https://github.com/amusi/CVPR2025-Papers-with-Code
CVPR 2025 论文和开源项目合集
https://github.com/amusi/CVPR2025-Papers-with-Code
computer-vision cvpr cvpr2020 cvpr2021 cvpr2022 cvpr2023 cvpr2024 cvpr2025 deep-learning image-processing image-segmentation machine-learning object-detection paper python semantic-segmentation transformer transformers visual-tracking
Last synced: about 2 months ago
JSON representation
CVPR 2025 论文和开源项目合集
- Host: GitHub
- URL: https://github.com/amusi/CVPR2025-Papers-with-Code
- Owner: amusi
- Created: 2020-02-26T06:04:25.000Z (about 5 years ago)
- Default Branch: main
- Last Pushed: 2025-02-27T09:35:33.000Z (about 2 months ago)
- Last Synced: 2025-02-27T12:41:39.186Z (about 2 months ago)
- Topics: computer-vision, cvpr, cvpr2020, cvpr2021, cvpr2022, cvpr2023, cvpr2024, cvpr2025, deep-learning, image-processing, image-segmentation, machine-learning, object-detection, paper, python, semantic-segmentation, transformer, transformers, visual-tracking
- Homepage:
- Size: 456 KB
- Stars: 18,856
- Watchers: 290
- Forks: 2,630
- Open Issues: 19
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# CVPR 2025 论文和开源项目合集(Papers with Code)
CVPR 2025 decisions are now available on OpenReview！22.1% = 2878 / 13008
> 注1：欢迎各位大佬提交issue，分享CVPR 2025论文和开源项目！
>
> 注2：关于往年CV顶会论文以及其他优质CV论文和大盘点，详见： https://github.com/amusi/daily-paper-computer-vision
>
> - [ECCV 2024](https://github.com/amusi/ECCV2024-Papers-with-Code)
> - [CVPR 2024](CVPR2024-Papers-with-Code.md)
欢迎扫码加入【CVer学术交流群】，可以获取CVPR 2025等最前沿工作！这是最大的计算机视觉AI知识星球！每日更新，第一时间分享最新最前沿的计算机视觉、AIGC、扩散模型、多模态、深度学习、自动驾驶、医疗影像和遥感等方向的学习资料，快加入学起来！
# 【CVPR 2025 论文开源目录】
- [3DGS(Gaussian Splatting)](#3DGS)
- [Avatars](#Avatars)
- [Backbone](#Backbone)
- [CLIP](#CLIP)
- [Mamba](#Mamba)
- [Embodied AI](#Embodied-AI)
- [GAN](#GAN)
- [GNN](#GNN)
- [多模态大语言模型(MLLM)](#MLLM)
- [大语言模型(LLM)](#LLM)
- [NAS](#NAS)
- [OCR](#OCR)
- [NeRF](#NeRF)
- [DETR](#DETR)
- [扩散模型(Diffusion Models)](#Diffusion)
- [ReID(重识别)](#ReID)
- [长尾分布(Long-Tail)](#Long-Tail)
- [Vision Transformer](#Vision-Transformer)
- [视觉和语言(Vision-Language)](#VL)
- [自监督学习(Self-supervised Learning)](#SSL)
- [数据增强(Data Augmentation)](#DA)
- [目标检测(Object Detection)](#Object-Detection)
- [异常检测(Anomaly Detection)](#Anomaly-Detection)
- [目标跟踪(Visual Tracking)](#VT)
- [语义分割(Semantic Segmentation)](#Semantic-Segmentation)
- [实例分割(Instance Segmentation)](#Instance-Segmentation)
- [全景分割(Panoptic Segmentation)](#Panoptic-Segmentation)
- [医学图像(Medical Image)](#MI)
- [医学图像分割(Medical Image Segmentation)](#MIS)
- [视频目标分割(Video Object Segmentation)](#VOS)
- [视频实例分割(Video Instance Segmentation)](#VIS)
- [参考图像分割(Referring Image Segmentation)](#RIS)
- [图像抠图(Image Matting)](#Matting)
- [图像编辑(Image Editing)](#Image-Editing)
- [Low-level Vision](#LLV)
- [超分辨率(Super-Resolution)](#SR)
- [去噪(Denoising)](#Denoising)
- [去模糊(Deblur)](#Deblur)
- [自动驾驶(Autonomous Driving)](#Autonomous-Driving)
- [3D点云(3D Point Cloud)](#3D-Point-Cloud)
- [3D目标检测(3D Object Detection)](#3DOD)
- [3D语义分割(3D Semantic Segmentation)](#3DSS)
- [3D目标跟踪(3D Object Tracking)](#3D-Object-Tracking)
- [3D语义场景补全(3D Semantic Scene Completion)](#3DSSC)
- [3D配准(3D Registration)](#3D-Registration)
- [3D人体姿态估计(3D Human Pose Estimation)](#3D-Human-Pose-Estimation)
- [3D人体Mesh估计(3D Human Mesh Estimation)](#3D-Human-Pose-Estimation)
- [医学图像(Medical Image)](#Medical-Image)
- [图像生成(Image Generation)](#Image-Generation)
- [视频生成(Video Generation)](#Video-Generation)
- [3D生成(3D Generation)](#3D-Generation)
- [视频理解(Video Understanding)](#Video-Understanding)
- [行为检测(Action Detection)](#Action-Detection)
- [具身智能(Embodied AI)](#Embodied)
- [文本检测(Text Detection)](#Text-Detection)
- [知识蒸馏(Knowledge Distillation)](#KD)
- [模型剪枝(Model Pruning)](#Pruning)
- [图像压缩(Image Compression)](#IC)
- [三维重建(3D Reconstruction)](#3D-Reconstruction)
- [深度估计(Depth Estimation)](#Depth-Estimation)
- [轨迹预测(Trajectory Prediction)](#TP)
- [车道线检测(Lane Detection)](#Lane-Detection)
- [图像描述(Image Captioning)](#Image-Captioning)
- [视觉问答(Visual Question Answering)](#VQA)
- [手语识别(Sign Language Recognition)](#SLR)
- [视频预测(Video Prediction)](#Video-Prediction)
- [新视点合成(Novel View Synthesis)](#NVS)
- [Zero-Shot Learning(零样本学习)](#ZSL)
- [立体匹配(Stereo Matching)](#Stereo-Matching)
- [特征匹配(Feature Matching)](#Feature-Matching)
- [暗光图像增强(Low-light Image Enhancement)](#Low-light)
- [场景图生成(Scene Graph Generation)](#SGG)
- [风格迁移(Style Transfer)](#ST)
- [隐式神经表示(Implicit Neural Representations)](#INR)
- [图像质量评价(Image Quality Assessment)](#IQA)
- [视频质量评价(Video Quality Assessment)](#Video-Quality-Assessment)
- [数据集(Datasets)](#Datasets)
- [新任务(New Tasks)](#New-Tasks)
- [其他(Others)](#Others)
# 3DGS(Gaussian Splatting)
# Avatars
# Backbone
# CLIP
# Mamba
**MambaVision: A Hybrid Mamba-Transformer Vision Backbone**
- Paper: https://arxiv.org/abs/2407.08083
- Code: https://github.com/NVlabs/MambaVision
**MobileMamba: Lightweight Multi-Receptive Visual Mamba Network**
- Paper: https://arxiv.org/abs/2411.15941
- Code: https://github.com/lewandofskee/MobileMamba
# Embodied AI
# GAN
# OCR
# NeRF
# DETR
# Prompt
# 多模态大语言模型(MLLM)
**LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences**
- Paper： https://arxiv.org/abs/2412.01292
- Code: https://github.com/Hoyyyaard/LSceneLLM
**DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution**
- Paper: https://arxiv.org/abs/2405.16071
- Code: https://github.com/callsys/DynRefer
# 大语言模型(LLM)
# NAS
# ReID(重识别)
# 扩散模型(Diffusion Models)
**TinyFusion: Diffusion Transformers Learned Shallow**
- Paper: https://arxiv.org/abs/2412.01199
- Code: https://github.com/VainF/TinyFusion
# Vision Transformer
# 视觉和语言(Vision-Language)
# 目标检测(Object Detection)
**LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models**
- Paper: https://arxiv.org/abs/2501.18954
- Code：https://github.com/iSEE-Laboratory/LLMDet
# 异常检测(Anomaly Detection)
# 目标跟踪(Object Tracking)
**Multiple Object Tracking as ID Prediction**
- Paper：https://arxiv.org/abs/2403.16848
- Code: https://github.com/MCG-NJU/MOTIP
# 医学图像(Medical Image)
# 医学图像分割(Medical Image Segmentation)
# 自动驾驶(Autonomous Driving)
**LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes**
- Project: https://ldkong.com/LiMoE
- Paper: https://arxiv.org/abs/2501.04004
- Code: https://github.com/Xiangxu-0103/LiMoE
# 3D点云(3D-Point-Cloud)
# 3D目标检测(3D Object Detection)
# 3D语义分割(3D Semantic Segmentation)
# 图像编辑(Image Editing)
**Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing**
- Paper: https://arxiv.org/abs/2411.16832
- Code: https://github.com/taco-group/FaceLock
# 视频编辑(Video Editing)
# Low-level Vision
# 超分辨率(Super-Resolution)
**AESOP: Auto-Encoded Supervision for Perceptual Image Super-Resolution**
- Paper: https://arxiv.org/abs/2412.00124
- Code: https://github.com/2minkyulee/AESOP-Auto-Encoded-Supervision-for-Perceptual-Image-Super-Resolution
# 去噪(Denoising)
## 图像去噪(Image Denoising)
# 3D人体姿态估计(3D Human Pose Estimation)
# 图像生成(Image Generation)
**Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models**
- Paper: https://arxiv.org/abs/2501.01423
- Code: https://github.com/hustvl/LightningDiT
**SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models**
- Paper: https://arxiv.org/abs/2412.04852
- Code: https://github.com/taco-group/SleeperMark
**TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation**
- Homepage: https://byteflow-ai.github.io/TokenFlow/
- Code: https://github.com/ByteFlow-AI/TokenFlow
- Paper:https://arxiv.org/abs/2412.03069
**PAR: Parallelized Autoregressive Visual Generation**
- Project: https://epiphqny.github.io/PAR-project/
- Paper: https://arxiv.org/abs/2412.15119
- Code: https://github.com/Epiphqny/PAR
# 视频生成(Video Generation)
**Identity-Preserving Text-to-Video Generation by Frequency Decomposition**
- Paper: https://arxiv.org/abs/2411.17440
- Code: https://github.com/PKU-YuanGroup/ConsisID
**Cinemo: Consistent and Controllable Image Animation with Motion Diffusion Models**
- Paper: https://arxiv.org/abs/2407.15642
- Code: https://github.com/maxin-cn/Cinemo
**X-Dyna: Expressive Dynamic Human Image Animation**
- Paper: https://arxiv.org/abs/2501.10021
- Code: https://github.com/bytedance/X-Dyna
**PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation**
- Paper: https://arxiv.org/pdf/2412.00596
- Code: https://github.com/pittisl/PhyT2V
**Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model**
- Project: https://liewfeng.github.io/TeaCache/
- Paper: https://arxiv.org/abs/2411.19108
- Code: https://github.com/ali-vilab/TeaCache
# 3D生成
**Generative Gaussian Splatting for Unbounded 3D City Generation**
- Project: https://haozhexie.com/project/gaussian-city
- Paper: https://arxiv.org/abs/2406.06526
- Code: https://github.com/hzxie/GaussianCity
# 视频理解(Video Understanding)
# 具身智能(Embodied AI)
**Universal Actions for Enhanced Embodied Foundation Models**
- Project: https://2toinf.github.io/UniAct/
- Paper: https://arxiv.org/abs/2501.10105
- Code: https://github.com/2toinf/UniAct
# 知识蒸馏(Knowledge Distillation)
# 深度估计(Depth Estimation)
**DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos**
- Project: https://depthcrafter.github.io
- Paper: https://arxiv.org/abs/2409.02095
- Code: https://github.com/Tencent/DepthCrafter
**MonSter: Marry Monodepth to Stereo Unleashes Power**
- Paper: https://arxiv.org/abs/2501.08643
- Code: https://github.com/Junda24/MonSter
# 立体匹配(Stereo Matching)
**MonSter: Marry Monodepth to Stereo Unleashes Power**
- Paper: https://arxiv.org/abs/2501.08643
- Code: https://github.com/Junda24/MonSter
# 暗光图像增强(Low-light Image Enhancement)
**HVI: A New color space for Low-light Image Enhancement**
- Paper: https://arxiv.org/abs/2502.20272
- Code: https://github.com/Fediory/HVI-CIDNet
- Demo: https://huggingface.co/spaces/Fediory/HVI-CIDNet_Low-light-Image-Enhancement_
# 场景图生成(Scene Graph Generation)
# 风格迁移(Style Transfer)
**StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements**
- Project: https://stylestudio-official.github.io/
- Paper: https://arxiv.org/abs/2412.08503
- Code: https://github.com/Westlake-AGI-Lab/StyleStudio
# 视频质量评价(Video Quality Assessment)
# 数据集(Datasets)
# 其他(Others)