awesome-computer-vision-papers

A list of papers and other resources on computer vision and deep learning.
https://github.com/tzxiang/awesome-computer-vision-papers

Last synced: 20 days ago
JSON representation

Reviews
SemanticSeg
- awesome-semantic-segmentation
- SemanticSegPaperCollection
- SegLoss
- Efficient-Segmentation-Networks
- U-Net and its variant code
- Code: Semantic Segmentation Suite in TensorFlow
- 2019IJCV
- 2019NIPS
- 2019NIPS
- 2019ICCV - based Pooling, ICCV2019 [[github]](https://github.com/sebgao/LIP) [[Notes]](https://zhuanlan.zhihu.com/p/85841067))
- 2019ICCV - tlabs.github.io/GSCNN/)
- 2019ICCV
- 2019ICCV
- 2019CVPR
- 2019CVPR
- 2019MICCAI
- 2019MICCAI
- 2018CVPR
- 2018ECCV
- 2018DLMIA
- 2017CVPR - gcn-global-convolutional-network-large-kernel-matters-semantic-segmentation-c830073492d2)
- 2017CVPR
- 2017CVPRW
- 2017ICRA
- awesome-panoptic-segmentation
- 2020ICRA
- 2019CVPR
- 2019CVPR
- 2019CVPR
- [Page
- [Page
- [Note
- align_corners
- arXiv202007
- arXiv202005
- arXiv202001
- [Blog
- arXiv2019.12
- arXiv2019.11
- arXiv2019.11
- arXiv2019.10 - Scale-Attention)
- arXiv2019.10
- arXiv2019.6
- arXiv2019.6
- arXiv2019.3
- arXiv2016.6
- 2019ICCV
- 2018CVPR
- 2018ECCV
- 2018ECCV
- 2015MICCAI
- arXiv2019.12
- 2019CVPR
- SegLoss
- SemanticSegPaperCollection
3DVision
- SfM
  - 2016ECCV
- Depth/StereoMatching
  - 2020PAMI
  - 2020ICLR
  - 2019ICCV
  - 2019CVPR
  - 2019CVPR
  - 2019IROS
  - 2018CVPR
  - 2018CVPR
  - 2017ICCV
  - 2016JMLR
  - 2019NIPS - SfMLearner-Release)
  - 2019ICCV
  - 2019ToG - ken-burns)
  - 2018CVPR
  - 2018CVPR
  - 2017CVPR - Pytorch) [[ClassProj]](https://cmsc733.github.io/2019/proj/p4/)
- Surface Reconstruction
  - 2014ECCV
  - ICCV15/IJCV17 - freiburg.de/people/ummenhof/multiscalefusion/)
- Review
  - [Proj&Code - dismbig, DISCO, LocalSymmetry, dataset ...)
- CameraPose
  - 2017CVPR
  - 2017CVPR
- 3D SemanticSeg
  - arXiv2019.12 - SPARK/Kimera-Semantics)
  - arXiv2019.11
  - arXiv2019.9
  - arXiv2019.7
  - 2019NIPS - han-lab/pvcnn)
DeepCNN
- Training
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - Blog
  - Tianfu Wu
  - a alternative to Batch Normalization
  - arXiv2019.3 - siyuan-qiao/WeightStandardization)
  - **IN**
  - **LN** - Normalization/)
  - 2019JBD
  - 2019JBD
  - 2018
  - Ping Luo
  - Blog
  - Blog
  - Talk
  - [Video
  - Training Tricks in Object Detection
  - arXiv2019.11
  - arXiv2019.8
  - arXiv2019.6
  - arXiv2019.4 - cv\)
  - 2019ICCV
  - 2019CVPR
  - Blog
  - [Notes
  - 2018NIPS
  - [Note1
  - Blog
  - Blog - augmentation-how-to-use-deep-learning-when-you-have-limited-data-part-2/)
  - 2019JBD
  - arXiv2019.11
  - arXiv202006 - vlc/FMix)
  - arXiv202001
  - arXiv2019.12
  - arXiv201911
  - arXiv201910
  - arXiv201906
  - 2019CVPR
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
  - 2019JBD
- Optimization
  - Summary of SGD，AdaGrad，Adadelta，Adam，Adamax，Nadam
  - Why Momentum Really Works, 2017
  - arXiv201912 - ODL++Optimization+Theory+for+Deep+Learning))
  - arXiv201912
  - arXiv2019.11
  - arXiv2019.5
  - arXiv2018.4
- Model
  - Blog
  - Blog
  - Blog
  - Blog
  - arXiv201909 - smxI_/view)
  - 2020AAAI
  - arXiv201912
  - For 2D/3D/Spherical
  - 2020ICLR - cnn) [[Intro]](https://zhuanlan.zhihu.com/p/104026923)
  - arXiv201911
  - 2019ICML
  - 2017CVPR
  - 2016CVPR - Q)
  - 1998ProcIEEE
  - Blog
  - Blog
  - arXiv201912
  - 2019BMVC
  - Blog
  - 2019ICCV
  - 2017
  - [Note
  - Blog
- Interpretation
  - Blog
  - arXiv2019.11
  - 2019NIPS
  - Blog
  - Blog
  - Blog
LowLevelVision
- 3D SemanticSeg
  - [Homepage
  - Blog
  - arXiv2019.7 - anwar/DRLN)
  - arXiv2019.4
  - 2019CVPR - learn-zoom)
  - 2019CVPR
  - 2018CVPR - Photo-Enhancer)
  - [Note
  - [Slides
  - arXiv2020.1 - Learning-on-Image-Denoising-An-overview)
  - Single Image Deraining - removal/codeless)
  - arXiv2019.9
  - arXiv2019.4
  - 2019Scirobotics
  - 2019ICCV
  - 2018CVPR
  - 2018Proj - OutPainting) [[PDF]](https://cs230.stanford.edu/projects_spring_2018/posters/8265861.pdf) [[Model]](https://drive.google.com/file/d/1548iAtsNf3wLSc1i5zYy-HX8_TW95wi_/view) [[Note]](http://www.sohu.com/a/244142600_473283)
  - Dongdong Chen
  - 2015 - neural-algorithm-of-artistic-style)
  - arXiv201910
  - 2018SIGGA
  - [Slides
Pedestrain/Crowd
- 3D SemanticSeg
  - arXiv2020.1 - Survey)
  - arXiv2019.1 - pedestrianattributes/)
  - arXiv201804
  - arXiv2019.9
  - arXiv2019.6 - iisc/lsc-cnn)
  - arXiv2019.3 - Net-Keras)
  - 2019ICCV
  - 2019SciAdvance
GenerativeNet
- 3D SemanticSeg
  - [Page
  - 深度学习中最常见GAN模型概览
  - Blog: One Day One GAN
  - [Page
  - [Page
  - arXiv202006
  - Blogg
  - arXiv2020.2
  - arXiv202001
  - arXiv201912 - v2)
  - arXiv2019.11
  - arXiv201907
  - arXiv2019.5
  - 2018ECCV
  - 2016ICML
Video Understanding
- 3D SemanticSeg
  - YOWO - tim/YOWO)
  - arXiv2019.7
  - arXiv2019.3 - looking-fast-and-slow)
  - 2019CVPR
  - 2019KDDW
Others
- Interpretation
  - arXiv201905 - MXNet]](https://github.com/deepinsight/insightface/tree/master/RetinaFace) [[Code-TF]](https://github.com/OFRIN/Tensorflow_RetinaFace)
  - 2019CVPR
  - 2019ICCV
  - 2018BMVC
  - arXiv201911
  - arXive202002
  - arXiv - trainer)
  - arXiv202003 - neural-weather-model-for-eight-hour.html) [Intro](https://mp.weixin.qq.com/s/GGLb7eA9a-5ZUNGs4X89iA)
  - 2019ICCV

Programming Languages

Python 31 Jupyter Notebook 4 C++ 3 Cuda 1

Categories

DeepCNN 98 SemanticSeg 55 3DVision 33 LowLevelVision 22 GenerativeNet 15 Others 9 Reviews 8 Pedestrain/Crowd 8 Video Understanding 5

Sub Categories

Training 62 3D SemanticSeg 55 Model 23 Depth/StereoMatching 16 Interpretation 15 Optimization 7 CameraPose 2 Surface Reconstruction 2 SfM 1 Review 1

Keywords

semantic-segmentation 9 pytorch 8 deep-learning 8 computer-vision 8 segmentation 4 panoptic-segmentation 4 3d-reconstruction 3 real-time-semantic-segmentation 2 stereo-vision 2 iccv2019 2 opensource 2 cityscapes 2 scene-parsing 2 semantic-segmentation-models 2 neural-networks 2 machine-learning 2 instance-segmentation 2 image-segmentation 2 bcai 1 upsampling 1 tensorflow 1 refinenet 1 python 1 iou 1 paper-resource 1 nv-tlabs 1 semantic-boundaries 1 cityscape 1 self-attention 1 cnn 1 convolutional-neural-networks 1 efficient 1 imagenet 1 lightweight 1 benchmark 1 deeplearning 1 evaluation 1 convolutional-networks 1 fully-convolutional-networks 1 interactive-segmentation 1 object-segmentation 1 promptable-segmentation 1 video-segmentation 1 camvid 1 driving-scene-understanding 1 efficient-segmentation-networks 1 lightweight-semantic-segmentation 1 scene-understanding 1 dataset 1 densenet 1