https://github.com/52cv/eccv-2022-papers

Last synced: 5 months ago
JSON representation
Host: GitHub
URL: https://github.com/52cv/eccv-2022-papers
Owner: 52CV
Created: 2022-01-19T02:46:26.000Z (over 4 years ago)
Default Branch: main
Last Pushed: 2022-12-28T02:57:12.000Z (over 3 years ago)
Last Synced: 2025-08-02T11:49:45.700Z (11 months ago)
Size: 2.43 MB
Stars: 135
Watchers: 6
Forks: 15
Open Issues: 0
Metadata Files:
- Readme: README.md
Awesome Lists containing this project

README

          # ECCV-2022-Papers

![9361c19ba6cbc5ae7be1fba8d82759b](https://user-images.githubusercontent.com/62801906/150054267-d54c28a4-f2de-4171-88df-d9820222a392.jpg)

官网链接：https://eccv2022.ecva.net/

截稿日期：2022年3月7日(9:59PM CET, 11:59AM PST)

会议日期：2022年10月24日-2022年10月28日

## 历年综述论文分类汇总戳这里↘️[CV-Surveys](https://github.com/52CV/CV-Surveys)施工中~~~~~~~~~~

## 2022 年论文分类汇总戳这里

↘️[CVPR-2022-Papers](https://github.com/52CV/CVPR-2022-Papers)

↘️[WACV-2022-Papers](https://github.com/52CV/WACV-2022-Papers)

↘️[ECCV-2022-Papers](https://github.com/52CV/ECCV-2022-Papers)

## 2021年论文分类汇总戳这里

↘️[ICCV-2021-Papers](https://github.com/52CV/ICCV-2021-Papers)

↘️[CVPR-2021-Papers](https://github.com/52CV/CVPR-2021-Papers)

## 2020 年论文分类汇总戳这里

↘️[CVPR-2020-Papers](https://github.com/52CV/CVPR-2020-Papers)

↘️[ECCV-2020-Papers](https://github.com/52CV/ECCV-2020-Papers)

## ❣❣❣另外打包下载ECCV 2022论文，可在【我爱计算机视觉】微信公众号后台回复“paper”。共计 1645 篇。分类完成

|:cat:|:dog:|:tiger:|:wolf:|

|------|------|------|------|

|[1.其它](#1)|[2.Image Segmentation(图像分割)](#2)|[3.Image Progress(图像处理)](#3)|[4.Image Captioning(图像字幕)](#4)|

|[5.Image/Video Retrieval(图像/视频检索)](#5)|[6.Object Detection(目标检测)](#6)|[7.Object Tracking(目标跟踪)](#7)|[8.3D(三维视觉)](#8)|

|[9.Human Pose Estimation(人体姿态估计)](#9)|[10.Pose Estimation(物体姿势估计)](#10)|[11.Video](#11)|[12.Action Detection(人体动作检测与识别)](#12)|

|[13.Human-Object Interaction(人物交互)](#13)|[14.Visual Answer Questions(视觉问答)](#14)|[15.Vision-Language(视觉语言)](#15)|[16.Transformer](#16)|

|[17.GAN](#17)|[18.Image-to-Image Translation(图像到图像翻译)](#18)|[19.Image Synthesis/Generation(图像合成)](#19)|[20.Face(人脸)](#20)|

|[21.Semi/self-supervised learning(半/自监督)](#21)|[22.OCR](#22)|[23.Medical Image(医学影像)](#23)|[24.UAV/Remote Sensing/Satellite Image(无人机/遥感/卫星图像)](#24)|

|[25.Autonomous vehicles(自动驾驶)](#25)|[26.Video/Image Super-Resolution(视频/图像超分辨率)](#26)|[27.Image Classification(图像分类)](#27)|[28.Neural Architecture Search(神经架构搜索)](#28)|

|[29.Re-identification(重识别)](#29)|[30.Optical Flow(光流)](#30)|[31.SLAM/Augmented Reality/Virtual Reality/Robotics(增强/虚拟现实/机器人)](#31)|[32.Point Cloud(点云)](#32)|

|[33.Model Compression/Knowledge Distillation/Pruning(模型压缩/知识蒸馏/剪枝)](#33)|[34.Meta-Learning(元学习)](#34)|[35.Feature Learning(联邦学习)](#35)|[36.Machine Learning(机器学习)](#36)|

|[37.Open-set Recognition(开集识别)](#37)|[38.Contrastive Learning(对比学习)](#38)|[39.Transfer Learning(迁移学习)](#39)|[40.Adversarial  Learning(对抗学习)](#40)|

|[41.Incremental Learning(增量学习)](#41)|[42.Reinforcement Learning(强化学习)](#42)|[43.Lifelong Learning(终生学习)](#43)|[44.Active Learning(主动学习)](#44)|

|[45.Metric Learning(度量学习)](#45)|[46.Continual Learning(持续学习)](#46)|[47.GNN/GCN(图神经网络)](#7)|[48.Semantic Correspondence(语义对应)](#48)|

|[49.Few/Zero-Shot Learning/Domain Generalization/Adaptation(小/零样本/域泛化/适应)](#49)|[50.Neural Rendering(渲染)](#50)|[51.Anomaly Detection(异常检测)](#51)|[52.Scene Flow Estimation(场景流估计)](#52)|

|[53.Dataset(数据集)](#53)|[54.View Generation(视图生成)](#54)|[55.Style Transfer(风格迁移)](#55)|[56.Sound](#56)|

|[57.Scene Graph Generation(场景图生成)](#57)|[58.Human Motion Prediction(人体动作预测)](#58)|[59.Image Matching(图像匹配)](#59)|[60.Data Augmentation(数据增强)](#60)|

|[61.Light Field(光学、几何、光场成像)](#61)|

## :trophy::trophy::trophy: 获奖论文

* 最佳论文奖

  * [On the Versatile Uses of Partial Distance Correlation in Deep Learning](https://arxiv.org/abs/2207.09684)
:star:[code](https://github.com/zhenxingjian/Partial_Distance_Correlation)

* 最佳论文荣誉奖

  * [A Level Set Theory for Neural Implicit Evolution under Explicit Flows](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136620699.pdf)

  * [Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields](https://virtualhumans.mpi-inf.mpg.de/papers/tiwari22posendf/posendf.pdf)
:star:[code](https://github.com/garvita-tiwari/PoseNDF)

* Koenderink Prize (test of time)

  * [A naturalistic open source movie for optical flow evaluation](https://files.is.tue.mpg.de/black/papers/ButlerECCV2012.pdf)

  * [Indoor Segmentation and Support Inference from RGBD Images](https://cs.nyu.edu/~silberman/papers/indoor_seg_support.pdf)

* Best Demo Award

  * [Using a Smartphone for Augmented Reality in a Classroom]
:tv:[video](https://www.youtube.com/watch?v=4pQC15Uzkck)

* Everingham Prize

  * 【The UCF101 and HMD51 dataset teams】&【Walter J. Scheirer 】

  



## 61.Light Field(光学、几何、光场成像)

* 相机相关

  * [Learned Monocular Depth Priors in Visual-Inertial Initialization](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136820537.pdf) 

  * 相机姿态估计

    * [E-Graph: Minimal Solution for Rigid Rotation with Extensibility Graphs](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136820298.pdf)

    * [Camera Pose Estimation and Localization with Active Audio Sensing](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136970266.pdf) 

 * 相机姿势

    * [Camera Pose Auto-Encoders for Improving Pose Regression](https://arxiv.org/abs/2207.05530)
:star:[code](https://github.com/yolish/camera-pose-auto-encoders)

  * 相机估计

    * [A Reliable Online Method for Joint Estimation of Focal Length and Camera Rotation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136610247.pdf)
:star:[code](https://github.com/ElderLab-York-University/OnlinefR)

  * 相机自动校准

    * [Camera Auto-Calibration from the Steiner Conic of the Fundamental Matrix](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136620419.pdf) 

  * 事件相机

    * [DVS-Voltmeter: Stochastic Process-Based Event Simulator for Dynamic Vision Sensors](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136670571.pdf)
:star:[code](https://github.com/Lynn0306/DVS-Voltmeter)  

    * [Selection and Cross Similarity for Event-Image Deep Stereo](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136920467.pdf)
:star:[code](https://github.com/Chohoonhee/SCSNet)

  * 相机重识别

    * [SC-wLS: Towards Interpretable Feed-forward Camera Re-localization](https://arxiv.org/abs/2210.12748)
:star:[code](https://github.com/XinWu98/SC-wLS)

  * 相机定位

    * [Towards Accurate Active Camera Localization](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136700119.pdf)
:star:[code](https://github.com/qhFang/AccurateACL)

* 光场

  * [Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertion](https://arxiv.org/abs/2208.09480)
:house:[project](https://nv-tlabs.github.io/outdoor-ar/)

  * [Synthesizing Light Field Video from Monocular Video](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136670158.pdf)
:star:[code](https://github.com/ShrisudhanG/Synthesizing-Light-Field-Video-from-Monocular-Video)

  * [NeILF: Neural Incident Light Field for Physically-Based Material Estimation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136910684.pdf)



## 60.Data Augmentation(数据增强)

* [TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers](https://arxiv.org/abs/2207.08409)
:star:[code](https://github.com/Sense-X/TokenMix)

* [Neuromorphic Data Augmentation for Training Spiking Neural Networks](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136670623.pdf)

* [3D Random Occlusion and Multi-layer Projection for Deep Multi-Camera Pedestrian Localization](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136700681.pdf)
:star:[code](https://github.com/xjtlu-cvlab/3DROM)



## 59.Image Matching(图像匹配)

* [ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer](https://arxiv.org/abs/2208.14201)
:house:[project](https://aspanformer.github.io/)

* [ECO-TR: Efficient Correspondences Finding Via Coarse-to-Fine Refinement](https://arxiv.org/abs/2209.12213)
:star:[code](https://github.com/dltan7/ECO-TR):house:[project](https://dltan7.github.io/ecotr/)



## 58.Human Motion Prediction(人体动作预测)

* [ERA: Expert Retrieval and Assembly for Early Action Prediction](https://arxiv.org/abs/2207.09675)

* [Overlooked Poses Actually Make Sense: Distilling Privileged Knowledge for Human Motion Prediction](https://arxiv.org/abs/2208.01302)

* [GIMO: Gaze-Informed Human Motion Prediction in Context](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136730675.pdf)
:star:[code](https://github.com/y-zheng18/GIMO) 

* [Diverse Human Motion Prediction Guided by Multi-level Spatial-Temporal Anchors](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136820244.pdf)
:star:[code](https://github.com/Sirui-Xu/STARS)

* 行动预测

  * [Rethinking Learning Approaches for Long-Term Action Anticipation](https://arxiv.org/abs/2210.11566)
:star:[code](https://github.com/Nmegha2601/anticipatr)

* 运动估计

  * [PREF: Predictability Regularized Neural Motion Fields](https://arxiv.org/abs/2209.10691)
:open_mouth:oral

* 人体运动合成

  * [Learning Uncoupled-Modulation CVAE for 3D Action-Conditioned Human Motion Synthesis](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136810707.pdf)

  * [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136820349.pdf)
:star:[code](https://guytevet.github.io/motionclip-page/)



## 57.Scene Graph Generation(场景图生成)

* [Panoptic Scene Graph Generation](https://arxiv.org/abs/2207.11247)
:star:[code](https://github.com/Jingkang50/OpenPSG/):house:[project](https://psgdataset.org/)

* [Meta Spatio-Temporal Debiasing for Video Scene Graph Generation](https://arxiv.org/abs/2207.11441)

* [Hierarchical Memory Learning for Fine-Grained Scene Graph Generation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136870263.pdf)

* [Fine-Grained Scene Graph Generation with Data Transfer](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136870402.pdf)
:star:[code](https://github.com/waxnkw/IETrans-SGG.pytorch)

* [Towards Open-Vocabulary Scene Graph Generation with Prompt-Based Finetuning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136880055.pdf)  



## 56.Sound

* [Learning Visual Styles from Audio-Visual Associations](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136970229.pdf)
:house:[project](https://tinglok.netlify.app/files/avstyle/)

* [Active Audio-Visual Separation of Dynamic Sound Sources](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136990543.pdf)
:house:[project](https://vision.cs.utexas.edu/projects/active-av-dynamic-separation/)

* 声源定位

  * [Localizing Visual Sounds the Easy Way](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136970212.pdf)
:star:[code](https://github.com/stoneMo/EZ-VSL)

* 有源扬声器检测

  * [End-to-End Active Speaker Detection](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136970124.pdf)

* 音频驱动的视频肖像生成

  * [Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136970105.pdf)
:open_mouth:oral:house:[project](https://alvinliu0.github.io/projects/SSP-NeRF)

* 视听分割

  * [Audio-Visual Segmentation](https://arxiv.org/abs/2207.05042)
:star:[code](https://github.com/OpenNLPLab/AVSBench)

  * [Audio—Visual Segmentation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136970378.pdf)
:star:[code](https://github.com/OpenNLPLab/AVSBench)

* 语音合成

  * [VisageSynTalk: Unseen Speaker Video-to-Speech Synthesis via Speech-Visage Feature Selection](https://arxiv.org/abs/2206.07458)

* 声音分离

  * [AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation](https://arxiv.org/abs/2207.10141)

  * [VoViT: Low Latency Graph-Based Audio-Visual Voice Separation Transformer](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136970304.pdf)
:house:[project](https://ipcv.github.io/VoViT/) 

 



## 55.Style Transfer(风格迁移)

* [CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer](https://arxiv.org/abs/2207.04808)
:open_mouth:oral:star:[code](https://github.com/JarrentWu1031/CCPL)

* [Learning Graph Neural Networks for Image Style Transfer](https://arxiv.org/abs/2207.11681)

* [ARF: Artistic Radiance Fields](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136910701.pdf)
:house:[project](https://www.cs.cornell.edu/projects/arf/)

* 图像风格化

  * [WISE: Whitebox Image Stylization by Example-based Learning](https://arxiv.org/abs/2207.14606)
:star:[code](https://github.com/winfried-loetzsch/wise)

* 发型迁移

  * [Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignment](https://arxiv.org/abs/2208.07765)
:star:[code](https://github.com/Taeu/Style-Your-Hair)



## 54.View Generation(视图生成)

* [InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images](https://arxiv.org/abs/2207.11148)
:open_mouth:oral

* [CompNVS: Novel View Synthesis with Scene Completion](https://arxiv.org/abs/2207.11467)

* [HDR-Plenoxels: Self-Calibrating High Dynamic Range Radiance Fields](https://arxiv.org/abs/2208.06787)
:star:[code](https://github.com/postech-ami/HDR-Plenoxels)

* [Neural Radiance Transfer Fields for Relightable Novel-View Synthesis with Global Illumination](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136770155.pdf) 

* [R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136910598.pdf)
:house:[project](https://snap-research.github.io/R2L)

* [NeXT: Towards High Quality Neural Radiance Fields via Multi-Skip Transformer](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136920069.pdf)
:star:[code](https://github.com/Crishawy/NeXT) 



## 53.Dataset(数据集)

* [The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136960549.pdf)
:sunflower:[dataset](https://github.com/allenai/sherlock)

* [Responsive Listening Head Generation: A Benchmark Dataset and Baseline](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136980122.pdf)
:sunflower:[dataset](https://project.mhzhou.com/vico)

* [Online Segmentation of LiDAR Sequences: Dataset and Algorithm](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136980298.pdf)
:sunflower:[dataset](https://romainloiseau.fr/helixnet/)

* [COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts](https://arxiv.org/abs/2207.04675)
:star:[code](https://github.com/ku21fan/COO-Comic-Onomatopoeia)
用于识别任意或截断文本的漫画拟声词数据集

* [BRACE: The Breakdancing Competition Dataset for Dance Motion Synthesis](https://arxiv.org/abs/2207.10120)
:sunflower:[dataset](https://github.com/dmoltisanti/brace/)
用于舞蹈动作合成的霹雳舞比赛数据集

* [CelebV-HQ: A Large-Scale Video Facial Attributes Dataset](https://arxiv.org/abs/2207.12393)
:sunflower:[dataset](https://github.com/CelebV-HQ/CelebV-HQ):house:[project](https://celebv-hq.github.io/)
一个大规模的视频人脸属性数据集

* [UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture](https://arxiv.org/abs/2208.01633)
:star:[code](https://github.com/hiroyasuakada/UnrealEgo):house:[project](https://4dqv.mpi-inf.mpg.de/UnrealEgo/)
用于鲁棒性以自我为中心的三维人类运动捕捉的新数据集

* [BEAT: A Large-Scale Semantic and Emotional Multi-modal Dataset for Conversational Gestures Synthesis](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136670605.pdf)
:sunflower:[dataset](https://pantomatrix.github.io/BEAT/)
:newspaper:[ECCV 2022 | 76小时动捕，最大规模数字人多模态数据集开源](https://mp.weixin.qq.com/s/dROXHNrEPNBZgYU6YzTEWQ)

* [MovieCuts: A New Dataset and Benchmark for Cut Type Recognition](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136670659.pdf)
:sunflower:[dataset](https://github.com/PardoAlejo/MovieCuts)
剪切类型识别  

* [A Real World Dataset for Multi-View 3D Reconstruction](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136680054.pdf)
:sunflower:[dataset](http://www.ocrtoc.org/#/3D-Reconstruction)
三维重建

* [Capturing, Reconstructing, and Simulating: The UrbanScene3D Dataset](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136680090.pdf)
:sunflower:[dataset](https://vcc.tech/UrbanScene3D)
城市场景重建

* [PartImageNet: A Large, High-Quality Dataset of Parts](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136680124.pdf)
分割

* [A-OKVQA: A Benchmark for Visual Question Answering Using World Knowledge](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136680141.pdf)
:sunflower:[dataset](https://allenai.org/project/a-okvqa/home)
VQA

* [OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136680158.pdf)

* [The Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editing](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136680195.pdf)
:sunflower:[dataset](https://github.com/dawitmureja/AVE)
视频编辑

* [ClearPose: Large-Scale Transparent Object Dataset and Benchmark](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136680372.pdf)
:sunflower:[dataset](https://github.com/opipari/ClearPose)
深度估计

* [AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136680405.pdf)
:sunflower:[dataset](https://github.com/kangyeolk/AnimeCeleb)
动画名人头像数据集

* [A Dense Material Segmentation Dataset for Indoor and Outdoor Scene Parsing](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136680440.pdf)
用于室内和室外场景解析的密集材料分割数据集

* [MimicME: A Large Scale Diverse 4D Database for Facial Expression Analysis](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136680457.pdf)
用于面部表情分析的大规模多样化4D数据库

* [Delving into Universal Lesion Segmentation: Method, Dataset, and Benchmark](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136680475.pdf)
:sunflower:[dataset](https://github.com/yuqiuyuqiu/KEN)
病变分割  



## 52.Scene Flow Estimation(场景流估计)

* [Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation](https://arxiv.org/abs/2207.07522)
:star:[code](https://github.com/cwc1260/BiFlow)

* [What Matters for 3D Scene Flow Network](https://arxiv.org/abs/2207.09143)
:star:[code](https://github.com/IRMVLab/3DFlow)

* [MonoPLFlowNet: Permutohedral Lattice FlowNet for Real-Scale 3D Scene Flow Estimation with Monocular Images](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136870316.pdf)  



## 51.Anomaly Detection(异常检测)

* [Registration based Few-Shot Anomaly Detection](https://arxiv.org/abs/2207.07361)
:open_mouth:oral:star:[code](https://github.com/MediaBrain-SJTU/RegAD)

* [Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection](https://arxiv.org/abs/2207.10948)
:star:[code](https://github.com/Beyond-Zw/DLAN-AC)

* [DSR – A Dual Subspace Re-Projection Network for Surface Anomaly Detection](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136910526.pdf)
:star:[code](https://github.com/VitjanZ/DSR_anomaly_detection) 

* [Locally Varying Distance Transform for Unsupervised Visual Anomaly Detection](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136900353.pdf)

* [SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136900389.pdf)
:star:[code](https://github.com/amazon-science/spot-diff)

* [HaloAE: An HaloNet based Local Transformer Auto-Encoder for Anomaly Detection and Localization](https://arxiv.org/abs/2208.03486)

* [Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136850107.pdf)
:star:[code](https://github.com/GaoangW/HSCL)

* 表面异常检测

  * [DSR -- A dual subspace re-projection network for surface anomaly detection](https://arxiv.org/abs/2208.01521)
:star:[code](https://github.com/VitjanZ/DSR_anomaly_detection)



## 50.Neural Rendering(渲染)

* [Relighting4D: Neural Relightable Human from Videos](https://arxiv.org/abs/2207.07104)
:star:[code](https://github.com/FrozenBurning/Relighting4D):house:[project](https://frozenburning.github.io/projects/relighting4d/):tv:[video](https://www.youtube.com/watch?v=NayAw89qtsY)

* [MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects](https://arxiv.org/abs/2207.08403)
:star:[code](https://github.com/JuewenPeng/MPIB):house:[project](https://juewenpeng.github.io/MPIB/) 

* [NeuMan: Neural Human Radiance Field from a Single Video](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136920400.pdf)
:star:[code](https://github.com/apple/ml-neuman)

* [Approximate Differentiable Rendering with Algebraic Surfaces](https://arxiv.org/abs/2207.10606)
:star:[code](https://github.com/leonidk/fuzzy-metaballs):house:[project](https://leonidk.github.io/fuzzy-metaballs/)

* [AdaNeRF: Adaptive Sampling for Real-time Rendering of Neural Radiance Fields](https://arxiv.org/abs/2207.10312)
:star:[code](https://github.com/thomasneff/AdaNeRF):house:[project](https://thomasneff.github.io/adanerf/) 

* [Generalizable Patch-Based Neural Rendering](https://arxiv.org/abs/2207.10662)
:open_mouth:oral:star:[code](https://github.com/google-research/google-research/tree/master/gen_patch_neural_rendering):house:[project](https://mohammedsuhail.net/gen_patch_neural_rendering/)

* [Deforming Radiance Fields with Cages](https://arxiv.org/abs/2207.12298)
:star:[code](https://github.com/xth430/deforming-nerf):house:[project](https://xth430.github.io/deforming-nerf/)

* [NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editing](https://arxiv.org/abs/2207.11911)
:open_mouth:oral:star:[code](https://github.com/zju3dv/neumesh):house:[project](https://zju3dv.github.io/neumesh/)  

* [ActiveNeRF: Learning where to See with Uncertainty Estimation](https://arxiv.org/abs/2209.08546)
:star:[code](https://github.com/LeapLabTHU/ActiveNeRF)

* [ARAH: Animatable Volume Rendering of Articulated Human SDFs](https://arxiv.org/abs/2210.10036)
:star:[code](https://github.com/taconite/arah-release):house:[project](https://neuralbodies.github.io/arah/)

* [LaTeRF: Label and Text Driven Object Radiance Fields](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136630021.pdf)

* [MoFaNeRF: Morphable Facial Neural Radiance Field](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136630267.pdf)
:star:[code](https://github.com/zhuhao-nju/mofanerf)

* [Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantification](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136630531.pdf) 

* [Sem2NeRF: Converting Single-View Semantic Masks to Neural Radiance Fields](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136740713.pdf)
:star:[code](https://donydchen.github.io/sem2nerf/)

* [KeypointNeRF: Generalizing Image-Based Volumetric Avatars Using Relative Spatial Encoding of Keypoints](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136750176.pdf)
:house:[project](https://markomih.github.io/KeypointNeRF)

* [ViewFormer: NeRF-Free Neural Rendering from Few Images Using Transformers](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136750195.pdf)
:star:[code](https://github.com/jkulhanek/viewformer)

* [GeoAug: Data Augmentation for Few-Shot NeRF with Geometry Constraints](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136770326.pdf)

* [SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136820712.pdf)
:star:[code](https://vita-group.github.io/SinNeRF/)  

* [BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-Scale Scene Rendering](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136920106.pdf)  



## 49.Few/Zero-Shot Learning/Domain Generalization/Adaptation(小/零样本/域泛化/适应)

* 小样本

  * [Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations](https://arxiv.org/abs/2207.07826)
:star:[code](https://github.com/WentaoChen0813/CDCS-FSL)

  * [Self-Supervision Can Be a Good Few-Shot Learner](https://arxiv.org/abs/2207.09176)
:star:[code](https://github.com/bbbdylan/unisiam)

  * [VizWiz-FewShot: Locating Objects in Images Taken by People With Visual Impairments](https://arxiv.org/abs/2207.11810)
:house:[project](https://vizwiz.org/)

  * [Contrastive Prototypical Network with Wasserstein Confidence Penalty](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136790654.pdf)
:star:[code](https://github.com/Haoqing-Wang/CPNWCP)

  * [tSF: Transformer-Based Semantic Filter for Few-Shot Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136800001.pdf)

  * [Worst Case Matters for Few-Shot Recognition](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136800092.pdf)

  * [Learning Instance and Task-Aware Dynamic Kernels for Few-Shot Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136800247.pdf)

  * [Self-Promoted Supervision for Few-Shot Transformer](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136800318.pdf)
:star:[code](https://github.com/DongSky/few-shot-vit)

  * [Coarse-to-Fine Incremental Few-Shot Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136910199.pdf)

  * [Improving Few-Shot Learning through Multi-task Representation Learning Theory](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136800423.pdf)

  * [TransVLAD: Focusing on Locally Aggregated Descriptors for Few-Shot Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136800509.pdf)

  * [Kernel Relative-Prototype Spectral Filtering for Few-Shot Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136800527.pdf)
:star:[code](https://github.com/zhangtao2022/DSFN)

  * [Uncertainty-DTW for Time Series and Sequences](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136810174.pdf)

* 零样本

  * [Temporal and cross-modal attention for audio-visual zero-shot learning](https://arxiv.org/abs/2207.09966)
:star:[code](https://github.com/ExplainableML/TCAF-GZSL)

  * [3D Compositional Zero-Shot Learning with DeCompositional Consensus](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136880704.pdf)

  * [Learning Invariant Visual Representations for Compositional Zero-Shot Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136840335.pdf) 
:star:[code](https://github.com/PRIS-CV/IVR)

* 域适应

  * [Prior Knowledge Guided Unsupervised Domain Adaptation](https://arxiv.org/abs/2207.08877)
:star:[code](https://github.com/tsun/KUDA)

  * [MoDA: Map Style Transfer for Self-Supervised Domain Adaptation of Embodied Agents](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136990332.pdf)

  * [CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation](https://arxiv.org/abs/2207.09778)
:star:[code](https://github.com/saltoricristiano/cosmix-uda)

  * [GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation](https://arxiv.org/abs/2207.09763)
:star:[code](https://github.com/saltoricristiano/gipso-sfouda)

  * [Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation](https://arxiv.org/abs/2207.10856)
:star:[code](https://github.com/Hongbin98/ProCA)

  * [MemSAC: Memory Augmented Sample Consistency for Large Scale Domain Adaptation](https://arxiv.org/abs/2207.12389)
:star:[code](https://github.com/ViLab-UCSD/MemSAC_ECCV2022):house:[project](https://tarun005.github.io/MemSAC/)

  * [Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation](https://arxiv.org/abs/2207.13247)
:star:[code](https://github.com/val-iisc/StickerDA):house:[project](https://sites.google.com/view/sticker-sfda)

  * [Combating Label Distribution Shift for Active Domain Adaptation](https://arxiv.org/abs/2208.06604)

  * [Uncertainty-guided Source-free Domain Adaptation](https://arxiv.org/abs/2208.07591)
:star:[code](https://github.com/roysubhankar/uncertainty-sfda)

  * [Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136910216.pdf)

  * [Unknown-Oriented Learning for Open Set Domain Adaptation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136930328.pdf)

  * [Burn after Reading: Online Adaptation for Cross-Domain Streaming Data](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136930396.pdf)
:star:[code](https://github.com/salesforce/burn-after-reading)

  * [Adversarial Partial Domain Adaptation by Cycle Inconsistency](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136930520.pdf)

  * [A Broad Study of Pre-training for Domain Generalization and Adaptation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136930609.pdf)

  * [Interpretable Open-Set Domain Adaptation via Angular Margin Separation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136940001.pdf)

  * [Contrastive Vicinal Space for Unsupervised Domain Adaptation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136940090.pdf)
:star:[code](https://github.com/NaJaeMin92/CoVi)

  * [Incomplete Multi-View Domain Adaptation via Channel Enhancement and Knowledge Transfer](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136940194.pdf)

  * [BMD: A General Class-Balanced Multicentric Dynamic Prototype Strategy for Source-Free Domain Adaptation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136940161.pdf)
:star:[code](https://github.com/ispc-lab/BMD)

* 域泛化

  * [Grounding Visual Representations with Texts for Domain Generalization](https://arxiv.org/abs/2207.10285)
:star:[code](https://github.com/mswzeus/GVRT)

  * [Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes](https://arxiv.org/abs/2207.11707)

  * [Attention Diversification for Domain Generalization](https://arxiv.org/abs/2210.04206)
:star:[code](https://github.com/hikvision-research/DomainGeneralization)

  * [Cross-Domain Ensemble Distillation for Domain Generalization](https://arxiv.org/abs/2211.14058)

  * [Domain Generalization by Mutual-Information Regularization with Pre-trained Models](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136830427.pdf)
:star:[code](https://github.com/kakaobrain/miro)

  * [MVDG: A Unified Multi-View Framework for Domain Generalization](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136870158.pdf)
:star:[code](https://github.com/koncle/MVDG) 



## 48.Semantic Correspondence(语义对应)

* [Demystifying Unsupervised Semantic Correspondence Estimation](https://arxiv.org/abs/2207.05054)
:star:[code](https://github.com/MehmetAygun/demistfy_correspondence):house:[project](https://mehmetaygun.github.io/demistfy.html)

* [Learning Semantic Correspondence with Sparse Annotations](https://arxiv.org/abs/2208.06974)



## 47.GNN/GCN(图神经网络)

* GCN

  * [End-to-end Graph-constrained Vectorized Floorplan Generation with Panoptic Refinement](https://arxiv.org/abs/2207.13268) 

  * [Learning Self-Prior for Mesh Denoising Using Dual Graph Convolutional Networks](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136630358.pdf)
:star:[code](https://github.com/astaka-pe/Dual-DMP)

  * [An Efficient Person Clustering Algorithm for Open Checkout-Free Groceries](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136980017.pdf)

* GNN

  * [Adversarial Label Poisoning Attack on Graph Neural Networks via Label Propagation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136650223.pdf)

  * [Equivariant Hypergraph Neural Networks](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136810086.pdf)
:star:[code](https://github.com/jw9730/ehnn) 



## 46.Continual Learning(持续学习)

* [Balancing Stability and Plasticity through Advanced Null Space in Continual Learning](https://arxiv.org/abs/2207.12061)
:open_mouth:oral 

* [Online Continual Learning with Contrastive Vision Transformer](https://arxiv.org/abs/2207.13516) 

* [Helpful or Harmful: Inter-Task Association in Continual Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136710518.pdf)

* [Theoretical Understanding of the Information Flow on Continual Learning Performance](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136720085.pdf)
:star:[code](https://github.com/Sekeh-Lab/InformationFlow-CL)

* [Transfer without Forgetting](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136830672.pdf)
:star:[code](https://github.com/mbosc/twf)

* [incDFM: Incremental Deep Feature Modeling for Continual Novelty Detection](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136850581.pdf)

* [Online Task-Free Continual Learning with Dynamic Sparse Distributed Memory](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136850721.pdf)
:star:[code](https://github.com/Julien-pour/Dynamic-Sparse-Distributed-Memory)

* [Discriminability-Transferability Trade-Off: An Information-Theoretic Perspective](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136860020.pdf)

* [CoSCL: Cooperation of Small Continual Learners Is Stronger than a Big One](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136860249.pdf)
:star:[code](https://github.com/lywang3081/CoSCL) 

* [DualPrompt: Complementary Prompting for Rehearsal-Free Continual Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136860617.pdf)
:star:[code](https://github.com/google-research/l2p) 



## 45.Metric Learning(度量学习)

* [DAS: Densely-Anchored Sampling for Deep Metric Learning](https://arxiv.org/abs/2208.00119)
:star:[code](https://github.com/lizhaoliu-Lec/DAS)

* [Posterior Refinement on Metric Matrix Improves Generalization Bound in Metric Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136860199.pdf)

* [A Non-Isotropic Probabilistic Take On Proxy-Based Deep Metric Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136860423.pdf)
:star:[code](https://github.com/ExplainableML/Probabilistic_Deep_Metric_Learning)



## 44.Active Learning(主动学习)

* [When Active Learning Meets Implicit Semantic Data Augmentation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136850056.pdf)

* [PT4AL: Using Self-Supervised Pretext Tasks for Active Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136860583.pdf)
:star:[code](https://github.com/johnsk95/PT4AL)  



## 43.Lifelong Learning(终生学习)

* [Anti-Retroactive Interference for Lifelong Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136840160.pdf)
:star:[code](https://github.com/bhrqw/ARI) 



## 42.Reinforcement Learning(强化学习)

* [Style-Agnostic Reinforcement Learning](https://arxiv.org/abs/2208.14863)
:star:[code](https://github.com/POSTECH-CVLab/style-agnostic-RL)

* [StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136990455.pdf)
:star:[code](https://github.com/elicassion/StARformer)

* [Learning Efficient Multi-agent Cooperative Visual Exploration](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136990491.pdf)
:house:[project](https://sites.google.com/view/maans)

* [DexMV: Imitation Learning for Dexterous Manipulation from Human Videos](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136990562.pdf)
:house:[project](https://yzqin.github.io/dexmv)  



## 41.Incremental Learning(增量学习)

* [Learning with Recoverable Forgetting](https://arxiv.org/abs/2207.08224)

* [Incremental Task Learning with Incremental Rank Updates](https://arxiv.org/abs/2207.09074)
:star:[code](https://github.com/CSIPlab/task-increment-rank-update)

* [DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning](https://arxiv.org/abs/2208.08112)

* 类增量

  * [Class-incremental Novel Class Discovery](https://arxiv.org/abs/2207.08605)
:star:[code](https://github.com/OatmealLiu/class-iNCD) 

  * [Long-Tailed Class Incremental Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136930486.pdf)
:star:[code](https://github.com/xialeiliu/Long-Tailed-CIL)

  * [Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay](https://arxiv.org/abs/2207.11213)

  * [Few-Shot Class-Incremental Learning from an Open-Set Perspective](https://arxiv.org/abs/2208.00147)
:star:[code](https://github.com/CanPeng123/FSCIL_ALICE)

  * [Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer](https://arxiv.org/abs/2208.03767)
:star:[code](https://github.com/richzhang/webpage-template):house:[project](https://cscct.github.io/)

  * [R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136830411.pdf)
:star:[code](https://github.com/jianzhangcs/R-DFCIL)

  * [FOSTER: Feature Boosting and Compression for Class-Incremental Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136850393.pdf)

  * [S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136850427.pdf)
:star:[code](https://github.com/JAYATEJAK/S3C)



## 40.Adversarial  Learning(对抗学习)

* [Prior-Guided Adversarial Initialization for Fast Adversarial Training](https://arxiv.org/abs/2207.08859)
:star:[code](https://github.com/jiaxiaojunQAQ/FGSM-PGI)
:newspaper:[ECCV 2022 | 一种基于先验指导的对抗样本初始化方法](https://mp.weixin.qq.com/s/8YhVEuE6kGIk8Qe6zxVW7w)

* [BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-Aided Adversarial Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136760331.pdf)
:star:[code](https://github.com/chang9711/BIPS)

* [Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustness](https://arxiv.org/abs/2207.10899)
:open_mouth:oral:star:[code](https://github.com/pantheon5100/DeACL)

* [RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN](https://arxiv.org/abs/2208.10608)
:star:[code](https://github.com/huyvnphan/ECCV2022-RIBAC)

* [Adversarial Coreset Selection for Efficient Robust Training](https://arxiv.org/abs/2209.05785)

* [Shape Matters: Deformable Patch Attack](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136640522.pdf)

* [Enhanced Accuracy and Robustness via Multi-Teacher Adversarial Distillation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136640577.pdf)
:star:[code](https://github.com/zhaoshiji123/MTARD)

* [GradAuto: Energy-Oriented Attack on Dynamic Neural Networks](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136640628.pdf)
:star:[code](https://github.com/JianhongPan/GradAuto) 

* [Learning Energy-Based Models with Adversarial Training](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136650204.pdf)

* [Revisiting Outer Optimization in Adversarial Training](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136650240.pdf)

* [One Size Does NOT Fit All: Data-Adaptive Adversarial Training](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136650070.pdf)
:star:[code](https://github.com/eccv2022daat/daat)

* [UniCR: Universally Approximated Certified Robustness via Randomized Smoothing](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136650086.pdf)  

* [ℓ∞-Robustness and Beyond:Unleashing Efficient Adversarial Training](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136710466.pdf)

* [Towards Efficient Adversarial Training on Vision Transformers](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136730307.pdf)

* [FrequencyLowCut Pooling - Plug & Play against Catastrophic Overfitting](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136740036.pdf)
:star:[code](https://github.com/GeJulia/flc_pooling)

* [TAFIM: Targeted Adversarial Attacks against Facial Image Manipulations](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136740053.pdf)
:house:[project](https://shivangi-aneja.github.io/projects/tafim)

* 对抗攻击

  * [Frequency Domain Model Augmentation for Adversarial Attack](https://arxiv.org/abs/2207.05382)
:star:[code](https://github.com/yuyang-long/SSA)

  * [Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal](https://arxiv.org/abs/2207.08178)
:star:[code](https://github.com/thinwayliu/Watermark-Vaccine)

  * [SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness](https://arxiv.org/abs/2207.12391)

  * [Scaling Adversarial Training to Large Perturbation Bounds](https://arxiv.org/abs/2210.09852)
:star:[code](https://github.com/val-iisc/OAAT)

  * [Towards Effective and Robust Neural Trojan Defenses via Input Filtering](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136650277.pdf)

  * [Exploiting the Local Parabolic Landscapes of Adversarial Losses to Accelerate Black-Box Adversarial Attack](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136650311.pdf)
:star:[code](https://github.com/HoangATran/BABIES)

  * [Robust Network Architecture Search via Feature Distortion Restraining](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136650120.pdf)

  * [Triangle Attack: A Query-Efficient Decision-Based Adversarial Attack](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136650153.pdf)
:star:[code](https://github.com/xiaosen-wang/TA)

  * [Adaptive Image Transformations for Transfer-Based Adversarial Attack](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136650001.pdf)

* 黑盒

  * [Black-Box Dissector: Towards Erasing-Based Hard-Label Model Stealing Attack](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136650188.pdf)

  * [An Invisible Black-Box Backdoor Attack through Frequency Domain](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136730396.pdf)
:star:[code](https://github.com/SoftWiser-group/FTrojan)

* 白盒

  * [Harmonizer: Learning to Perform White-Box Image and Video Harmonization](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136750688.pdf)

* 对抗样本

  * [Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136640714.pdf)
:star:[code](https://github.com/ShawnXYang/C-GSP)



## 39.Transfer Learning(迁移学习)

* [Factorizing Knowledge in Neural Networks](https://arxiv.org/abs/2207.03337)
:star:[code](https://github.com/Adamdad/KnowledgeFactor)

* [SecretGen: Privacy Recovery on Pre-trained Models via Distribution Discrimination](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136650137.pdf)
:star:[code](https://github.com/AI-secure/SecretGen) 

* [How Stable Are Transferability Metrics Evaluations?](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136940296.pdf)

* [Language-Driven Artistic Style Transfer](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136960708.pdf)

* [MultiMAE: Multi-modal Multi-task Masked Autoencoders](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136970341.pdf)
:house:[project](https://multimae.epfl.ch/) 



## 38.Contrastive Learning(对比学习)

* [Network Binarization via Contrastive Learning](https://arxiv.org/abs/2207.02970)
:star:[code](https://github.com/42Shawn/CMIM)

* [Adversarial Contrastive Learning via Asymmetric InfoNCE](https://arxiv.org/abs/2207.08374)
:star:[code](https://github.com/yqy2001/A-InfoNCE)

* [Fast-MoCo: Boost Momentum-based Contrastive Learning with Combinatorial Patches](https://arxiv.org/abs/2207.08220)
:star:[code](https://github.com/orashi/Fast-MoCo)

* [Contrastive Learning for Diverse Disentangled Foreground Generation](https://arxiv.org/abs/2211.02707)

* [Decoupled Contrastive Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136860653.pdf)

* [Joint Learning of Localized Representations from Medical Images and Reports](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136860670.pdf)

* [Contrasting Quadratic Assignments for Set-Based Representation Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136870087.pdf)

* [Generative Subgraph Contrast for Self-Supervised Graph Representation Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136900090.pdf)
:star:[code](https://github.com/yh-han/GSC) 

 



## 37.Open-set Recognition(开集识别)

* [DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognition](https://arxiv.org/abs/2207.02606)

* [Difficulty-Aware Simulator for Open Set Recognition](https://arxiv.org/abs/2207.10024)
:star:[code](https://github.com/wjun0830/Difficulty-Aware-Simulator) 



## 36.Machine Learning(机器学习)

* [Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning](https://arxiv.org/abs/2207.02598)



## 35.Feature Learning(联邦学习)

* [SphereFed: Hyperspherical Federated Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136860161.pdf)

* [Image Coding for Machines with Omnipotent Feature Learning](https://arxiv.org/abs/2207.01932)

* [Addressing Heterogeneity in Federated Learning via Distributional Transformation](https://arxiv.org/abs/2210.15025)
:star:[code](https://github.com/hyhmia/DisTrans)

* [FedLTN: Federated Learning for Sparse and Personalized Lottery Ticket Networks](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136720069.pdf)

* [Improving Generalization in Federated Learning by Seeking Flat Minima](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136830636.pdf)

* [AdaBest: Minimizing Client Drift in Federated Learning via Adaptive Bias Estimation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136830690.pdf) 



## 34.Meta-Learning(元学习)

* [Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning Approach](https://arxiv.org/abs/2207.10188)

* [Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributions](https://arxiv.org/abs/2209.01501)  

* [Learning to Weight Samples for Dynamic Early-exiting Networks](https://arxiv.org/abs/2209.08310)
:star:[code](https://github.com/LeapLabTHU/L2W-DEN)  

* [Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning](https://arxiv.org/abs/2209.13635)
:star:[code](https://github.com/xingpingdong/PL-CFE)



## 33.Model Compression/Knowledge Distillation/Pruning(模型压缩/知识蒸馏/剪枝)

* 知识蒸馏

  * [Knowledge Condensation Distillation](https://arxiv.org/abs/2207.05409)
:star:[code](https://github.com/dzy3/KCD)

  * [FedX: Unsupervised Federated Learning with Cross Knowledge Distillation](https://arxiv.org/abs/2207.09158)
:star:[code](https://github.com/Sungwon-Han/FEDX)

  * [Black-box Few-shot Knowledge Distillation](https://arxiv.org/abs/2207.12106)
:star:[code](https://github.com/nphdang/FS-BBT)

  * [Efficient One Pass Self-distillation with Zipf's Label Smoothing](https://arxiv.org/abs/2207.12980)
:star:[code](https://github.com/megvii-research/zipfls)

  * [MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition](https://arxiv.org/abs/2208.05768)
:star:[code](https://github.com/winycg/Self-KD-Lib)

  * [Switchable Online Knowledge Distillation](https://arxiv.org/abs/2209.04996)
:star:[code](https://github.com/hfutqian/SwitOKD)

  * [Distilling the Undistillable: Learning from a Nasty Teacher](https://arxiv.org/abs/2210.11728)
:star:[code](https://github.com/surgan12/NastyAttacks)

  * [Masked Generative Distillation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136710053.pdf)
:star:[code](https://github.com/yzd-v/MGD)

  * [DistPro: Searching a Fast Knowledge Distillation Process via Meta Optimization](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136940211.pdf)
:star:[code](https://github.com/xdeng7/DistPro)

  * [Personalized Education: Blind Knowledge Distillation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136940262.pdf)
:star:[code](https://github.com/Xiang-Deng-DL/PEBKD)

  * [Prune Your Model before Distill It](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136710120.pdf)
:star:[code](https://github.com/ososos888/prune-then-distill)

  * [IDa-Det: An Information Discrepancy-Aware Distillation for 1-Bit Detectors](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136710347.pdf)
:star:[code](https://github.com/SteveTsui/IDa-Det)

  * [Deep Ensemble Learning by Diverse Knowledge Distillation for Fine-Grained Object Classification](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136710501.pdf)

  * [A Fast Knowledge Distillation Framework for Visual Recognition](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136840663.pdf)
:house:[project](http://zhiqiangshen.com/projects/FKD/index.html)

  * [Self-Regulated Feature Learning via Teacher-Free Feature Distillation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136860337.pdf)
:house:[project](https://lilujunai.github.io/Teacher-free-Distillation/)

* 量化

  * [Synergistic Self-supervised and Quantization Learning](https://arxiv.org/abs/2207.05432)
:open_mouth:oral:star:[code](https://github.com/megvii-research/SSQL-ECCV2022)

  * [PalQuant: Accelerating High-precision Networks on Low-precision Accelerators](https://arxiv.org/abs/2208.01944)
:star:[code](https://github.com/huqinghao/PalQuant)

  * [Fine-Grained Data Distribution Alignment for Post-Training Quantization](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136710070.pdf)
:star:[code](https://github.com/zysxmu/FDDA)

  * [Symmetry Regularization and Saturating Nonlinearity for Robust Quantization](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136710207.pdf)

  * [Mixed-Precision Neural Network Quantization via Learned Layer-Wise Importance](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136710260.pdf)

  * [Non-uniform Step Size Quantization for Accurate Post-Training Quantization](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136710657.pdf)
:star:[code](https://github.com/sogh5/SubsetQ)

  * [Towards Accurate Network Quantization with Equivalent Smooth Regularizer](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136710726.pdf)

  * [Explicit Model Size Control and Relaxation via Smooth Regularization for Mixed-Precision Quantization](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136720001.pdf)

  * [BASQ: Branch-Wise Activation-Clipping Search Quantization for Sub-4-Bit Neural Networks](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136720017.pdf)
:star:[code](https://github.com/HanByulKim/BASQ)

  * [RDO-Q: Extremely Fine-Grained Channel-Wise Quantization via Rate-Distortion Optimization](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136720156.pdf)

  * [PTQ4ViT: Post-Training Quantization for Vision Transformers with Twin Uniform Quantization](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136720190.pdf)

* 剪枝

  * [FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classification](https://arxiv.org/abs/2207.10888)
:star:[code](https://github.com/Bernardo1998/FairGRAPE)

  * [Bayesian Optimization with Clustering and Rollback for CNN Auto Pruning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136830480.pdf)
:star:[code](https://github.com/fanhanwei/BOCR)

  * [Trainability Preserving Neural Structured Pruning](https://arxiv.org/abs/2207.12534)
:star:[code](https://github.com/mingsun-tse/TPP)

  * [Interpretations Steered Network Pruning via Amortized Inferred Saliency Maps](https://arxiv.org/abs/2209.02869)
:star:[code](https://github.com/Alii-Ganjj/InterpretationsSteeredPruning)

  * [Data-Free Backdoor Removal Based on Channel Lipschitzness](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136650171.pdf)
:star:[code](https://github.com/rkteddy/channel-Lipschitzness-based-pruning)

  * [Multi-Granularity Pruning for Model Acceleration on Mobile Devices](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136710483.pdf)

  * [Ensemble Knowledge Guided Sub-network Search and Fine-Tuning for Filter Pruning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136710568.pdf)

  * [Soft Masking for Cost-Constrained Channel Pruning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136710640.pdf)
:star:[code](https://github.com/NVlabs/SMCP)

  * [Towards Ultra Low Latency Spiking Neural Networks for Vision and Sequential Tasks Using Temporal Pruning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136710709.pdf)

  * [CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN Execution](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136800634.pdf)

  * [Filter Pruning via Feature Discrimination in Deep Neural Networks](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136810241.pdf)

* 轻量级

  * [Learning Extremely Lightweight and Robust Model with Differentiable Constraints on Sparsity and Condition Number](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136640679.pdf) 

* MC

  * [Patch Similarity Aware Data-Free Quantization for Vision Transformers](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136710154.pdf)
:star:[code](https://github.com/zkkli/PSAQ-ViT)

  * [Disentangled Differentiable Network Pruning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136710329.pdf)

  * [Weight Fixing Networks](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136710416.pdf)

  * [SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136710618.pdf)
:star:[code](https://github.com/PeiyanFlying/SPViT)



## 32.Point Cloud(点云)

* [Few 'Zero Level Set'-Shot Learning of Shape Signed Distance Functions in Feature Space](https://arxiv.org/abs/2207.04161)

* [FH-Net: A Fast Hierarchical Network for Scene Flow Estimation on Real-World Point Clouds](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136990210.pdf)
:star:[code](https://github.com/pigtigger/FH-Net)

* [Dynamic 3D Scene Analysis by Point Cloud Accumulation](https://arxiv.org/abs/2207.12394)
:star:[code](https://github.com/prs-eth/PCAccumulation):house:[project](https://shengyuh.github.io/eccv22/index.html)

* [Point Cloud Compression with Sibling Context and Surface Priors](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136980726.pdf)

* [LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136990070.pdf)

* [Point MixSwap: Attentional Point Cloud Mixing via Swapping Matched Structural Divisions](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136890587.pdf)
:star:[code](https://github.com/ardianumam/PointMixSwap)

* [MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136950523.pdf)
:star:[code](https://github.com/SxJyJay/MORE)

* [Bottom Up Top down Detection Transformers for Language Grounding in Images and Point Clouds](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136960411.pdf)
:house:[project](https://butd-detr.github.io/)

* [PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Trees](https://arxiv.org/abs/2208.05962)
:star:[code](https://github.com/immortalCO/PointTree)

* [Learning to Generate Realistic LiDAR Point Clouds](https://arxiv.org/abs/2209.03954)
:house:[project](https://www.zyrianov.org/lidargen/)

* [PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds](https://arxiv.org/abs/2210.13428)

* [SPE-Net: Boosting Point Cloud Analysis via Rotation Robustness Enhancement](https://arxiv.org/abs/2211.08250)
:star:[code](https://github.com/ZhaofanQiu/SPE-Net)

* [Resolution-Free Point Cloud Sampling Network with Data Distillation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136620053.pdf)
:star:[code](https://github.com/Tianxinhuang/PCDNet)

* [diffConv: Analyzing Irregular Point Clouds with an Irregular View](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136630375.pdf)
:star:[code](https://github.com/mmmmimic/diffConvNet)

* [GraphFit: Learning Multi-Scale Graph-Convolutional Representation for Point Cloud Normal Estimation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136920646.pdf)
:star:[code](https://github.com/UestcJay/GraphFit)

* [Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136930715.pdf)
:star:[code](https://github.com/Gorilla-Lab-SCUT/QS3) 

* [PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136630392.pdf)
:star:[code](https://github.com/unknownue/pdflow)

* [Shape-Pose Disentanglement Using SE(3)-Equivariant Vector Neurons](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136630461.pdf)

* [Revisiting Point Cloud Simplification: A Learnable Feature Preserving Approach](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136620573.pdf)

* [Masked Autoencoders for Point Cloud Self-Supervised Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136620591.pdf)
:star:[code](https://github.com/Pang-Yatian/Point-MAE)

* [Masked Discrimination for Self-Supervised Learning on Point Clouds](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136620645.pdf)
:star:[code](https://github.com/haotian-liu/MaskPoint)

* [Meta-Sampler: Almost-Universal yet Task-Oriented Sampling for Point Clouds](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136620682.pdf)
:star:[code](https://github.com/ttchengab/MetaSampler)

* [Efficient Point Cloud Analysis Using Hilbert Curve](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136620717.pdf)

* [RFNet-4D: Joint Object Reconstruction and Flow Estimation from 4D Point Clouds](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136830036.pdf)
:star:[code](https://github.com/hkust-vgd/RFNet-4D)   

* 3D点云

  * [Autoregressive 3D Shape Generation via Canonical Mapping](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136630091.pdf)
:star:[code](https://github.com/AnjieCheng/CanonicalVAE)

  * [Point Cloud Domain Adaptation via Masked Local 3D Structure Prediction](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136630159.pdf)
:star:[code](https://github.com/VITA-Group/MLSP)

  * [Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attacks](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136630230.pdf)
:star:[code](https://github.com/WoodwindHu/GSDA)

  * [Unsupervised Learning of 3D Semantic Keypoints with Mutual Reconstruction](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136620521.pdf)
:star:[code](https://github.com/YYYYYHC/Learning-Semantic-Keypoints-with-Mutual-Reconstruction)

  * [Few-Shot Class-Incremental Learning for 3D Point Cloud Objects](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136800194.pdf)
:star:[code](https://github.com/townim-faisal/FSCIL-3D)

  * [Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136970625.pdf)
:star:[code](https://github.com/chenfengxu714/image2point)

  * [Manifold Adversarial Learning for Cross-Domain 3D Shape Representation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136860266.pdf)

* 点云定位

  * [CPO: Change Robust Panorama to Point Cloud Localization](https://arxiv.org/abs/2207.05317)

* 点云分割

  * [Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation](https://arxiv.org/abs/2207.09084)

  * [Efficient Point Cloud Segmentation with Geometry-Aware Sparse Networks](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136990193.pdf)

* 点云补全  

  * [SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer](https://arxiv.org/abs/2207.10315)
:star:[code](https://github.com/hrzhou2/seedformer)   

  * [FBNet: Feedback Network for Point Cloud Completion](https://arxiv.org/abs/2210.03974)
:open_mouth:oral:star:[code](https://github.com/hikvision-research/3DVision/) 

  * [Optimization over Disentangled Encoding: Unsupervised Cross-Domain Point Cloud Completion via Occlusion Factor Manipulation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136620504.pdf)
:star:[code](https://github.com/azuki-miho/OptDE)

* 点云配准

  * [SuperLine3D: Self-supervised Line Segmentation and Description for LiDAR Point Cloud](https://arxiv.org/abs/2208.01925)
:star:[code](https://github.com/zxrzju/SuperLine3D) 

  * [Improving RGB-D Point Cloud Registration by Learning Multi-scale Local Linear Transformation](https://arxiv.org/abs/2208.14893)
:star:[code](https://github.com/514DNA/LLT)

  * [PointCLM: A Contrastive Learning-Based Framework for Multi-Instance Point Cloud Registration](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136690586.pdf)
:star:[code](https://github.com/phdymz/PointCLM)

  * [PCR-CG: Point Cloud Registration via Deep Explicit Color and Geometry](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136700439.pdf)  

* 点云重建

  * [Learning to Train a Point Cloud Reconstruction Network without Matching](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136610177.pdf)
:star:[code](https://github.com/Tianxinhuang/PCLossNet)

* 点云分类

  * [Improving Adversarial Robustness of 3D Point Cloud Classification Models](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136640663.pdf)
:star:[code](https://github.com/GuanlinLee/CCNAMS)

* 点云理解

  * [PointMixer: MLP-Mixer for Point Cloud Understanding](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136870611.pdf)
:star:[code](https://github.com/LifeBeyondExpectations/ECCV22-PointMixer) 



## 31.SLAM/Augmented Reality/Virtual Reality/Robotics(增强/虚拟现实/机器人)

* 增强现实

  * [LaMAR: Benchmarking Localization and Mapping for Augmented Reality](https://arxiv.org/abs/2210.10770)
:star:[code](https://github.com/microsoft/lamar-benchmark):house:[project](https://lamar.ethz.ch/)

* VR

  * [LiP-Flow: Learning Inference-Time Priors for Codec Avatars via Normalizing Flows in Latent Space](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136860091.pdf)

  * human volumetric capture(容积捕获)

    * [AvatarCap: Animatable Avatar Conditioned Monocular Human Volumetric Capture](https://arxiv.org/abs/2207.02031)
:star:[code](https://github.com/lizhe00/AvatarCap):house:[project](http://www.liuyebin.com/avatarcap/avatarcap.html)

* 虚拟试穿

  * [Single Stage Virtual Try-on via Deformable Attention Flows](https://arxiv.org/abs/2207.09161) 

  * [Dress Code: High-Resolution Multi-Category Virtual Try-On](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136680337.pdf)
:star:[code](https://github.com/aimagelab/dress-code)

  * [High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136770208.pdf)
:star:[code](https://github.com/sangyun884/HR-VITON) 

* 视觉定位(相机姿势估计)

  * [MeshLoc: Mesh-Based Visual Localization](https://arxiv.org/abs/2207.10762)
:star:[code](https://github.com/tsattler/meshloc_release)

* 机器人

  * [Visual Cross-View Metric Localization with Dense Uncertainty Estimates](https://arxiv.org/abs/2208.08519)
:star:[code](https://github.com/tudelft-iv/CrossViewMetricLocalization)



## 30.Optical Flow(光流)

* [Secrets of Event-Based Optical Flow](https://arxiv.org/abs/2207.10022)
:star:[code](https://github.com/tub-rip/event_based_optical_flow)

* [Deep 360∘ Optical Flow Estimation Based on Multi-Projection Fusion](https://arxiv.org/abs/2208.00776)

* [Learning Omnidirectional Flow in 360-degree Video via Siamese Representation](https://arxiv.org/abs/2208.03620)
:house:[project](https://siamlof.github.io/)

* [Video Interpolation by Event-driven Anisotropic Adjustment of Optical Flow](https://arxiv.org/abs/2208.09127)

* [Learning Omnidirectional Flow in 360° Video via Siamese Representation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136680546.pdf)
:house:[project](https://siamlof.github.io/)

* [FlowFormer: A Transformer Architecture for Optical Flow](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136770672.pdf)

* [Complementing Brightness Constancy with Deep Networks for Optical Flow Prediction](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136810120.pdf)

* [Disentangling Architecture and Training for Optical Flow](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136820159.pdf)
:house:[project](https://autoflow-google.github.io/)

* [A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical Flow](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136820177.pdf)
:open_mouth:oral:star:[code](https://github.com/cv-stuttgart/PCFA)

* [Optical Flow Training under Limited Label Budget via Active Learning](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136820400.pdf)
:star:[code](https://github.com/duke-vision/optical-flow-active-learning-release)

* [S2F2: Single-Stage Flow Forecasting for Future Multiple Trajectories Prediction](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136820593.pdf)

* [Semi-Supervised Learning of Optical Flow by Flow Supervisor](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136950298.pdf)
:star:[code](https://github.com/iwbn/flow-supervisor)

* [Deep 360° Optical Flow Estimation Based on Multi-Projection Fusion](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136950332.pdf)



## 29.Re-identification(重识别)

* 重识别  

  * [Negative Samples are at Large: Leveraging Hard-distance Elastic Loss for Re-identification](https://arxiv.org/abs/2207.09884)

  * [PASS: Part-Aware Self-Supervised Pre-training for Person Re-identification](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136740192.pdf)
:star:[code](https://github.com/CASIA-IVA-Lab/PASS-reID)

  * [Adaptive Cross-Domain Learning for Generalizable Person Re-identification](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136740209.pdf)
:star:[code](https://github.com/peterzpy/ACL-DGReID)

  * [Dynamically Transformed Instance Normalization Network for Generalizable Person Re-identification](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136740279.pdf)

  * [Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136740362.pdf)
:star:[code](https://github.com/xbq1994/META)

  * [Modality Synergy Complement Learning with Cascaded Aggregation for Visible-Infrared Person Re-identification](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136740450.pdf)
:star:[code](https://github.com/bitreidgroup/VI-ReID-MSCLNet)

  * [Cross-Modality Transformer for Visible-Infrared Person Re-identification](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136740467.pdf)

  * [Optimal Transport for Label-Efficient Visible-Infrared Person Re-identification](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136840091.pdf) 
:star:[code](https://github.com/wjm-wjm/OTLA-ReID) 

  * [Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136860371.pdf)

* 行人搜索

  * [OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search](https://arxiv.org/abs/2207.10320)
:house:[project](https://cvlab.yonsei.ac.kr/projects/OIMNetPlus/)

  * [A Simple and Robust Correlation Filtering Method for Text-Based Person Search](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136950719.pdf)
:star:[code](https://github.com/Suo-Wei/SRCF)

  * [Domain Adaptive Person Search](https://arxiv.org/abs/2207.11898)
:open_mouth:oral:star:[code](https://github.com/caposerenity/DAPS)

* 人群计数

  * [An End-to-End Transformer Model for Crowd Localization](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136610037.pdf)
:house:[project](https://dk-liang.github.io/CLTR/)

  * [Completely Self-Supervised Crowd Counting via Distribution Matching](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136910180.pdf)

  * [Calibration-Free Multi-View Crowd Counting](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136690224.pdf)

* Visual Search

  * [Target-Absent Human Attention](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136640051.pdf)
:star:[code](https://github.com/cvlab-stonybrook/Target-absent-Human-Attention)

* 步态识别

  * [MetaGait: Learning to Learn an Omni Sample Adaptive Representation for Gait Recognition](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136650350.pdf)

  * [GaitEdge: Beyond Plain End-to-End Gait Recognition for Better Practicality](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136650368.pdf)
:star:[code](https://github.com/ShiqiYu/OpenGait)



## 28.Neural Architecture Search(神经架构搜索)

* [SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning](https://arxiv.org/abs/2207.03677)
:star:[code](https://github.com/RICE-EIC/SuperTickets)

* [UniNet: Unified Architecture Search with Convolution, Transformer, and MLP](https://arxiv.org/abs/2207.05420)
:star:[code](https://github.com/Sense-X/UniNet)

* [ScaleNet: Searching for the Model to Scale](https://arxiv.org/abs/2207.07267)
:star:[code](https://github.com/luminolx/ScaleNet)

* [CLOSE: Curriculum Learning On the Sharing Extent Towards Better One-shot NAS](https://arxiv.org/abs/2207.07868)
:star:[code](https://github.com/walkerning/aw_nas)

* [Towards Regression-Free Neural Networks for Diverse Compute Platforms](https://arxiv.org/abs/2209.13740)

* [LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds](https://arxiv.org/abs/2210.05018)

* [U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136720172.pdf)
:star:[code](https://github.com/yuezuegu/UBoostNAS)

* [A Max-Flow Based Approach for Neural Architecture Search](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136800668.pdf)

* [ViTAS: Vision Transformer Architecture Search](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136810138.pdf)

* [Learning Where to Look – Generative NAS Is Surprisingly Efficient](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136830257.pdf)
:star:[code](https://github.com/jovitalukasik/AG-Net)

* [Neural Architecture Search for Spiking Neural Networks](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136840036.pdf) 

* [Data-Free Neural Architecture Search via Recursive Label Calibration](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136840386.pdf)
:star:[code](https://github.com/liuzechun/Data-Free-NAS)  



## 27.Image Classification(图像分类)

* [Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset](https://arxiv.org/abs/2207.10664)
:star:[code](https://github.com/visipedia/ssw60)

* [Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels](https://arxiv.org/abs/2207.14476)
:star:[code](https://github.com/uitrbn/TSCSI_IDN)

* [Not All Models Are Equal: Predicting Model Transferability in a Self-Challenging Fisher Space](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136940279.pdf)
:star:[code](https://github.com/TencentARC/SFDA)

* [Constructing Balance from Imbalance for Long-tailed Image Recognition](https://arxiv.org/abs/2208.02567)
:star:[code](https://github.com/silicx/DLSA)

* [No Token Left Behind: Explainability-Aided Image Classification and Generation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136720329.pdf)
:star:[code](https://github.com/apple/ml-no-token-left-behind)

* [Interpretable Image Classification with Differentiable Prototypes Assignment](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136720346.pdf)
:star:[code](https://github.com/gmum/ProtoPool)

* [Rotation Regularization without Rotation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136850632.pdf)
:star:[code](https://github.com/tk1980/StatRot)

* [Revisiting a kNN-based Image Classification System with High-capacity Storage](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136970449.pdf)

* [In Defense of Image Pre-training for Spatiotemporal Recognition](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136850665.pdf)
:star:[code](https://github.com/UCSC-VLAA/Image-Pretraining-for-Video)

* [Augmenting Deep Classifiers with Polynomial Neural Networks](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136850682.pdf) 

* [A Dataset Generation Framework for Evaluating Megapixel Image Classifiers & their Explanations](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136720416.pdf)

* [Cartoon Explanations of Image Classifiers](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136720439.pdf)

* [Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image Classification](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136800108.pdf)
:house:[project](https://kaiyi.me/p/hgrnet.html)

* [SSBNet: Improving Visual Recognition Efficiency by Adaptive Sampling](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136810224.pdf)

* [AutoMix: Unveiling the Power of Mixup for Stronger Classifiers](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136840435.pdf)

* [MaxViT: Multi-axis Vision Transformer](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136840453.pdf)
:star:[code](https://github.com/google-research/maxvit)

* [Self-Feature Distillation with Uncertainty Modeling for Degraded Image Recognition](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136840544.pdf)

* [Three Things Everyone Should Know about Vision Transformers](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136840490.pdf)

* [RealPatch: A Statistical Matching Framework for Model Patching with Real Samples](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136850144.pdf)
:star:[code](https://github.com/wearepal/RealPatch)

* [TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNs](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136850255.pdf)
:star:[code](https://github.com/shantanuj/TDAM_Top_down_attention_module)

* [Automatic Check-Out via Prototype-Based Classifier Learning from Single-Product Exemplars](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136850273.pdf)
:star:[code](https://github.com/Hao-Chen-NJUST/PSP)

* [Embedding Contrastive Unsupervised Features to Cluster in- and Out-of-Distribution Noise in Corrupted Image Datasets](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136910389.pdf)

* [Unsupervised Few-Shot Image Classification by Learning Features into Clustering Space](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136910406.pdf)

* 小样本图像分类

  * [Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation](https://arxiv.org/abs/2207.06989)
:star:[code](https://github.com/remiMZ/HTS-ECCV22) 

  * [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://arxiv.org/abs/2207.09519)
:star:[code](https://github.com/gaopengcuhk/Tip-Adapter)

  * [Adversarial Feature Augmentation for Cross-domain Few-shot Classification](https://arxiv.org/abs/2208.11021)
:star:[code](https://github.com/youthhoo/AFA_For_Few_shot_learning)

  * [Few-Shot Classification with Contrastive Learning](https://arxiv.org/abs/2209.08224)

* 多标签分类

  * [Hyperspherical Learning in Multi-Label Classification](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136850038.pdf)
:star:[code](https://github.com/TencentYoutuResearch/MultiLabel-HML)

* 长尾分类

  * [SAFA: Sample-Adaptive Feature Augmentation for Long-Tailed Image Classification](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136840578.pdf)

  * [Invariant Feature Learning for Generalized Long-Tailed Classification](https://arxiv.org/abs/2207.09504)
:star:[code](https://github.com/KaihuaTang/Generalized-Long-Tailed-Benchmarks.pytorch)

  * [Tackling Long-Tailed Category Distribution Under Domain Shifts](https://arxiv.org/abs/2207.10150)
:star:[code](https://github.com/guxiao0822/lt-ds):house:[project](https://xiaogu.site/LTDS/)

  * [Identifying Hard Noise in Long-Tailed Sample Distribution](https://arxiv.org/abs/2207.13378)
:open_mouth:oral:star:[code](https://github.com/yxymessi/H2E-Framework) 

  * [On Multi-Domain Long-Tailed Recognition, Imbalanced Domain Generalization and Beyond](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136800054.pdf)
:star:[code](https://github.com/YyzHarry/multi-domain-imbalance)

* 视觉分类

  * [Visual Knowledge Tracing](https://arxiv.org/abs/2207.10157)
:star:[code](https://github.com/nkondapa/VisualKnowledgeTracing)

* 细粒度识别

  * [Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanism](https://arxiv.org/abs/2208.00617)
:star:[code](https://github.com/GANPerf/SAM)  

  * [Zero-Shot Attribute Attacks on Fine-Grained Recognition Models](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136650257.pdf)

  * [Where to Focus: Investigating Hierarchical Attention Relationship for Fine-Grained Visual Classification](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136840056.pdf)
:star:[code](https://github.com/visiondom/CHRF) 

* 长尾识别

  * [Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-tailed Learning](https://arxiv.org/abs/2208.10043)
:star:[code](https://github.com/VipaiLab/vMF_OP)

  * [Breadcrumbs: Adversarial Class-Balanced Sampling for Long-Tailed Recognition](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136840628.pdf)
:star:[code](https://github.com/BoLiu-SVCL/Breadcrumbs)

  * [VL-LTR: Learning Class-Wise Visual-Linguistic Representation for Long-Tailed Visual Recognition](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136850072.pdf)
:star:[code](https://github.com/ChangyaoTian/VL-LTR)



## 26.Video/Image Super-Resolution(视频/图像超分辨率)

* 跨模态超分辨率

  * [Learning Mutual Modulation for Self-Supervised Cross-Modal Super-Resolution](https://arxiv.org/abs/2207.09156)
:star:[code](https://github.com/palmdong/MMSR)

* 图像超分辨率

  * [Image Super-Resolution with Deep Dictionary](https://arxiv.org/abs/2207.09228)
:star:[code](https://github.com/shuntama/srdd)

  * [CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution](https://arxiv.org/abs/2207.10345)
:star:[code](https://github.com/Cheeun/CADyQ)

  * [Reference-based Image Super-Resolution with Deformable Attention Transformer](https://arxiv.org/abs/2207.11938)
:star:[code](https://github.com/caojiezhang/DATSR) 

  * [KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution](https://arxiv.org/abs/2209.10305)
:star:[code](https://github.com/jiahong-fu/KXNet)

  * [Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images](https://arxiv.org/abs/2210.04198)  

  * [Boosting Event Stream Super-Resolution with a Recurrent Neural Network](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136660461.pdf) 

  * [Learning Series-Parallel Lookup Tables for Efficient Image Super-Resolution](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136770309.pdf)
:star:[code](https://github.com/zhjy2016/SPLUT)

  * [Efficient Long-Range Attention Network for Image Super-Resolution](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136770653.pdf)
:star:[code](https://github.com/xindongzhang/ELAN)

  * [Metric Learning Based Interactive Modulation for Real-World Super-Resolution](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136770727.pdf)
:star:[code](https://github.com/TencentARC/MM-RealSR)

  * [Dynamic Dual Trainable Bounds for Ultra-Low Precision Super-Resolution Networks](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136780001.pdf)
:star:[code](https://github.com/zysxmu/DDTB)

  * [Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136780106.pdf)
:star:[code](https://github.com/Yuehan717/PDASR)

  * [Uncertainty Learning in Kernel Estimation for Multi-stage Blind Image Super-Resolution](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136780141.pdf)

  * [MuLUT: Cooperating Multiple Look-Up Tables for Efficient Image Super-Resolution](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136780234.pdf)

  * [Adaptive Patch Exiting for Scalable Single Image Super-Resolution](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136780286.pdf)
:star:[code](https://github.com/littlepure2333/APE)

  * [From Face to Natural Image: Learning Real Degradation for Blind Image Super-Resolution](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136780368.pdf)
:star:[code](https://github.com/csxmli2016/ReDegNet)

  * [Unfolded Deep Kernel Estimation for Blind Image Super-Resolution](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136780493.pdf)
:star:[code](https://github.com/natezhenghy/UDKE)

  * [Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136780563.pdf)
:star:[code](https://github.com/csjliang/DASR)

  * [Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136780599.pdf)
:star:[code](https://github.com/cszhilu1998/SelfDZSR)

  * [Restore Globally, Refine Locally: A Mask-Guided Scheme to Accelerate Super-Resolution Networks](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136790072.pdf)
:star:[code](https://github.com/huxiaotaostasy/MGA-scheme)

  * [Compiler-Aware Neural Architecture Search for On-Mobile Real-Time Super-Resolution](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136790089.pdf)
:star:[code](https://github.com/wuyushuwys/compiler-aware-nas-sr)

  * [KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136790230.pdf)
:star:[code](https://github.com/jiahong-fu/KXNet)

  * [ARM: Any-Time Super-Resolution Method](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136790248.pdf)
:star:[code](https://github.com/chenbong/ARM-Net)

  * [D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136790370.pdf)
:star:[code](https://github.com/megvii-research/D2C-SR)

  * [RRSR:Reciprocal Reference-Based Image Super-Resolution with Progressive Feature Alignment and Selection](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136790637.pdf)

* 视频超分辨率

  * [Towards Interpretable Video Super-Resolution via Alternating Optimization](https://arxiv.org/abs/2207.10765)
:star:[code](https://github.com/caojiezhang/DAVSR)

  * [Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution](https://arxiv.org/abs/2208.03012)
:star:[code](https://github.com/researchmm/FTVSR)

  * [Real-RawVSR: Real-World Raw Video Super-Resolution with a Benchmark Dataset](https://arxiv.org/abs/2209.12475)
:star:[code](https://github.com/zmzhang1998/Real-RawVSR)

  * [A Codec Information Assisted Framework for Efficient Compressed Video Super-Resolution](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136770224.pdf) 



## 25.Autonomous vehicles(自动驾驶)

* 车辆轨迹预测

  * [Hierarchical Latent Structure for Multi-Modal Vehicle Trajectory Forecasting](https://arxiv.org/abs/2207.04624)
:star:[code](https://github.com/d1024choi/HLSTrajForecast)

  * [Action-based Contrastive Learning for Trajectory Prediction](https://arxiv.org/abs/2207.08664)

  * [D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights](https://arxiv.org/abs/2207.10398)
:star:[code](https://github.com/VTP-TL/D2-TPred)

  * [AdvDO: Realistic Adversarial Attacks for Trajectory Prediction](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136650036.pdf)
:house:[project](https://robustav.github.io/RobustPred/)

* 自动驾驶

  * [ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning](https://arxiv.org/abs/2207.07601)
:star:[code](https://github.com/OpenPerceptionX/ST-P3)

  * [Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction](https://arxiv.org/abs/2207.09705)

  * [Dfferentiable Raycasting for Self-supervised Occupancy Forecasting](https://arxiv.org/abs/2210.01917)
:star:[code](https://github.com/tarashakhurana/emergent-occ-forecasting)

  * [Self-Distillation for Robust LiDAR Semantic Segmentation in Autonomous Driving](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136880650.pdf)
:star:[code](https://github.com/jialeli1/lidarseg3d)

  * [V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136990106.pdf)
:star:[code](https://github.com/DerrickXuNu/v2x-vit)

  * [Radatron: Accurate Detection Using Multi-Resolution Cascaded MIMO Radar](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136990157.pdf)
:house:[project](https://jguan.page/Radatron/)

  * [Rethinking Closed-Loop Training for Autonomous Driving](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136990259.pdf)

  * [Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving](https://arxiv.org/abs/2210.08061)

  * [KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136980332.pdf)
:open_mouth:oral:house:[project](https://lasnik.github.io/king/)

  * [InAction: Interpretable Action Decision Making for Autonomous Driving](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136980365.pdf)
:star:[code](https://github.com/scottjingtt/InAction)

  * [CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136980399.pdf)
:house:[project](https://coda-dataset.github.io/)

  * [Unsupervised Semantic Segmentation of Urban Scenes via Cross-Modal Distillation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136980469.pdf)
:open_mouth:oral:house:[project](https://vobecant.github.io/DriveAndSegment/)

  * [StretchBEV: Stretching Future Instance Prediction Spatially and Temporally](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136980436.pdf)
:house:[project](https://kuis-ai.github.io/stretchbev/)

  * [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136690001.pdf)
:star:[code](https://github.com/zhiqi-li/BEVFormer)

  * [Point Cloud Compression with Range Image-Based Entropy Model for Autonomous Driving](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136820315.pdf)

* 轨迹预测

  * [Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction](https://arxiv.org/abs/2207.09953)
:star:[code](https://github.com/inhwanbae/GPGraph)

  * [Aware of the History: Trajectory Forecasting with the Local Behavior Data](https://arxiv.org/abs/2207.09646)
:star:[code](https://github.com/Kay1794/LocalBehavior-based-trajectory-prediction)

  * [Social-SSL: Self-Supervised Cross-Sequence Representation Learning Based on Transformers for Multi-agent Trajectory Prediction](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136820227.pdf)
:star:[code](https://github.com/Sigta678/Social-SSL)

  * [Sequential Multi-View Fusion Network for Fast LiDAR Point Motion Estimation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136820282.pdf)

  * [Social-Implicit: Rethinking Trajectory Prediction Evaluation and the Effectiveness of Implicit Maximum Likelihood Estimation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136820451.pdf)
:star:[code](https://github.com/abduallahmohamed/Social-Implicit/)

  * [View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136820661.pdf)
:star:[code](https://github.com/cocoon2wong/Vertical) 

  * [PreTraM: Self-Supervised Pre-training via Connecting Trajectory and Map](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136990034.pdf)
:star:[code](https://github.com/chenfengxu714/PreTraM)

* 车道线检测

  * [RCLane: Relay Chain Prediction for Lane Detection](https://arxiv.org/abs/2207.09399)

  * [PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136980539.pdf)
:open_mouth:oral:star:[code](https://github.com/OpenPerceptionX/PersFormer_3DLane)

  * [Lane Detection Transformer Based on Multi-Frame Horizontal and Vertical Attention and Visual Transformer Module](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136990001.pdf)

* 行人轨迹预测

  * [Human Trajectory Prediction via Neural Social Physics](https://arxiv.org/abs/2207.10435)
:star:[code](https://github.com/realcrane/Human-Trajectory-Prediction-via-Neural-Social-Physics)

  * [SocialVAE: Human Trajectory Prediction Using Timewise Latents](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136640504.pdf)
:star:[code](https://github.com/xupei0610/SocialVAE):house:[project](https://motion-lab.github.io/SocialVAE/)

* 车辆重识别

  * [Unstructured Feature Decoupling for Vehicle Re-identification](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136740328.pdf)
:star:[code](https://github.com/damo-cv/UFDN-Reid)  



## 24.UAV/Remote Sensing/Satellite Image(无人机/遥感/卫星图像)

* 遥感

  * [Tomography of Turbulence Strength Based on Scintillation Imaging](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136670464.pdf) 

  * [TD-Road: Top-Down Road Network Extraction with Holistic Graph Construction](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136690553.pdf)

 * 航空视频识别

  * [FAR: Fourier Aerial Video Recognition](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136970644.pdf)
:house:[project](https://gamma.umd.edu/researchdirections/aerialvideos/far/) 



## 23.Medical Image(医学影像)

* [The Surprisingly Straightforward Scene Text Removal Method With Gated Attention and Region of Interest Generation: A Comprehensive Prominent Model Analysis](https://arxiv.org/abs/2210.07489)
:star:[code](https://github.com/wyndwarrior/autoregressive-bbox):house:[project](https://bbox.yuxuanliu.com/)

* 医学图像分割

  * [Personalizing Federated Medical Image Segmentation via Local Calibration](https://arxiv.org/abs/2207.04655)
:star:[code](https://github.com/jcwang123/FedLC)

  * [Learning Topological Interactions for Multi-Class Medical Image Segmentation](https://arxiv.org/abs/2207.09654)
:open_mouth:oral:star:[code](https://github.com/TopoXLab/TopoInteraction)

  * [Generalizable Medical Image Segmentation via Random Amplitude Mixup and Domain-Specific Image Restoration](https://arxiv.org/abs/2208.03901)
:star:[code](https://github.com/zzzqzhou/RAM-DSIR)

  * [PointScatter: Point Set Representation for Tubular Structure Extraction](https://arxiv.org/abs/2209.05774)
:open_mouth:oral:star:[code](https://github.com/zhangzhao2022/pointscatter)

  * [Dual Contrastive Learning with Anatomical Auxiliary Supervision for Few-Shot Medical Image Segmentation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136800406.pdf)
:star:[code](https://github.com/cvszusparkle/AAS-DCL_FS)

  * [Auto-FedRL: Federated Hyperparameter Optimization for Multi-Institutional Medical Image Segmentation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136810431.pdf)
:star:[code](https://github.com/nvidia/nvflare/research/auto-fedrl)

  * [Med-DANet: Dynamic Architecture Network for Efficient Medical Volumetric Segmentation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136810499.pdf)
:star:[code](https://github.com/Wenxuan-1119/Med-DANet)

  * [CXR Segmentation by AdaIN-Based Domain Adaptation and Knowledge Distillation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136810619.pdf)

* 放射科报告生成

  * [Cross-modal Prototype Driven Network for Radiology Report Generation](https://arxiv.org/abs/2207.04818)
:star:[code](https://github.com/Markin-Wang/XProNet)

* 密集预测

  * [ConCL: Concept Contrastive Learning for Dense Prediction Pre-training in Pathology Images](https://arxiv.org/abs/2207.06733)
:star:[code](https://github.com/TencentAILabHealthcare/ConCL)

* retinal image matching(视网膜图像匹配)

  * [Semi-Supervised Keypoint Detector and Descriptor for Retinal Image Matching](https://arxiv.org/abs/2207.07932)
:star:[code](https://github.com/ruc-aimc-lab/SuperRetina)

* 支架追踪

  * [Robust Landmark-based Stent Tracking in X-ray Fluoroscopy](https://arxiv.org/abs/2207.09933)

* 病变检测

  * [Check and Link: Pairwise Lesion Correspondence Guides Mammogram Mass Detection](https://arxiv.org/abs/2209.05809)

* 医学图像分析

  * [UniMiSS: Universal Medical Self-Supervised Learning via Breaking Dimensionality Barrier](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136810551.pdf)
:star:[code](https://github.com/YtongXie/UniMiSS-code)

  * [K-SALSA: K-Anonymous Synthetic Averaging of Retinal Images via Local Style Alignment](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136810652.pdf)
:star:[code](https://github.com/hcholab/k-salsa)

* 医学图像分类

  * [Differentiable Zooming for Multiple Instance Learning on Whole-Slide Images](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136810689.pdf)
:star:[code](https://github.com/histocartography/zoommil)

  * 疾病分类

    * [RadioTransformer: A Cascaded Global-Focal Transformer for Visual Attention-Guided Disease Classification](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136810669.pdf)
:star:[code](https://github.com/bmi-imaginelab/radiotransformer)

* 医学关键点定位

  * [One-Shot Medical Landmark Localization by Edge-Guided Transform and Noisy Landmark Refinement](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136810466.pdf)
:star:[code](https://github.com/GoldExcalibur/EdgeTrans4Mark)



## 22.OCR

* [Levenshtein OCR](https://arxiv.org/abs/2209.03594)

* 文本识别

  * [Text-DIAE: Degradation Invariant Autoencoders for Text Recognition and Document Enhancement](https://arxiv.org/abs/2203.04814)

* 手写数学表达式识别

  * [CoMER: Modeling Coverage for Transformer-based Handwritten Mathematical Expression Recognition](https://arxiv.org/abs/2207.04410)
:star:[code](https://github.com/Green-Wood/CoMER)

  * [When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition](https://arxiv.org/abs/2207.11463)
:star:[code](https://github.com/LBH1024/CAN)

* 场景文本检测

  * [Scene Text Recognition with Permuted Autoregressive Sequence Models](https://arxiv.org/abs/2207.06966)
:star:[code](https://github.com/baudm/parseq)

  * [Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting](https://arxiv.org/abs/2207.06694)
:star:[code](https://github.com/hikopensource/DAVAR-Lab-OCR/)

  * [SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition](https://arxiv.org/abs/2207.10256)

  * [Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning](https://arxiv.org/abs/2207.11934)

  * [Contextual Text Block Detection towards Scene Text Understanding](https://arxiv.org/abs/2207.12955)
:house:[project](https://sg-vilab.github.io/publication/xue2022contextual/)  

  * [Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition](https://arxiv.org/abs/2208.00438)
:open_mouth:oral:star:[code](https://github.com/xdxie/WordArt)

  * [GLASS: Global to Local Attention for Scene-Text Spotting](https://arxiv.org/abs/2208.03364)
:star:[code](https://github.com/amazon-research/glass-text-spotting)

  * [Multi-Granularity Prediction for Scene Text Recognition](https://arxiv.org/abs/2209.03592)

  * [Pure Transformer with Integrated Experts for Scene Text Recognition](https://arxiv.org/abs/2211.04963)

  * [Background-Insensitive Scene Text Recognition with Text Semantic Segmentation](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136850161.pdf)

  * [Detecting Tampered Scene Text in the Wild](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136880214.pdf)
:star:[code](https://github.com/wangyuxin87/Tampered-IC13)

  * [Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136880282.pdf)

  * [TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizers](https://www.ecva.net/pape
ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Awesome

https://github.com/52cv/eccv-2022-papers

Awesome Lists containing this project

README
