extreme-assistant/cvpr2024-paper-code-interpretation

cvpr2024/cvpr2023/cvpr2022/cvpr2021/cvpr2020/cvpr2019/cvpr2018/cvpr2017 论文/代码/解读/直播合集，极市团队整理

• 推荐阅读：
  
  • ICCV2021/2019/2017 论文/代码/解读/直播合集
  • 2020-2021年计算机视觉综述论文汇总
    
  • 国内外优秀的计算机视觉团队汇总

---

cvpr2024/cvpr2023/cvpr2022/cvpr2021/cvpr2020/cvpr2019/cvpr2018/cvpr2017（Papers/Codes/Project/Paper reading）

论文解读+技术直播汇总：https://bbs.cvmart.net/articles/4368
论文分类汇总：https://bbs.cvmart.net/articles/4267

2000~2021年历届CVPR最佳论文代码，解读等汇总：http://bbs.cvmart.net/topics/665/CVPR-Best-Paper

目录

11. CVPR2024论文解读汇总
10. CVPR2023最新信息及论文下载
9. CVPR2022最新信息及论文下载
8. CVPR2021论文下载/代码/解读/直播
7. CVPR2021论文分方向盘点
6. CVPR2020论文下载/代码/解读/直播
5. CVPR2020论文分方向盘点
4. CVPR2019全部论文下载/开源代码
3. CVPR2019论文分方向盘点
2. CVPR2019论文直播分享
1. CVPR2018/CVPR2017

11. CVPR2024论文解读汇总

• CVPR2024论文解读汇总
• CVPR2024工作直播分享汇总

10.CVPR2023论文下载/代码/解读/直播(持续更新)

• Papers/Codes/Project/PaperReading／Demos/直播分享／论文分享会等
  
• CVPR2023 论文解读汇总 + 技术直播汇总
  

9.CVPR2022论文下载/代码/解读/直播(持续更新)

• Papers/Codes/Project/PaperReading／Demos/直播分享／论文分享会等
  
• CVPR2022 论文解读汇总 + 技术直播汇总
  
• CVPR2022 Oral论文汇总/解读（待更新）
  
  

8.CVPR2021论文下载/代码/解读/直播(持续更新)

• Papers/Codes/Project/PaperReading／Demos/直播分享／论文分享会等
  
  • CVPR2021全部论文下载（共1661篇） 提取码：su7e
• CVPR2021 论文解读汇总 + 技术直播汇总
  
• CVPR2021 Oral论文汇总/解读
  
  

7.CVPR2021论文分方向盘点

• 一文看尽CVPR2021 2D 目标检测论文（27篇）
• 一文看尽CVPR2021 图像异常检测论文（6篇）
• 一文看尽CVPR2021 伪装目标检测+旋转目标检测论文（6篇）
• CVPR2021 论文大盘点：全景分割论文汇总（共15篇）
• CVPR2021 论文大盘点：人员重识别汇总（共26篇）
• CVPR2021 论文大盘点：行人技术汇总（共7篇）
• CVPR2021 论文大盘点：医学影像汇总（共22篇）
• CVPR2021 论文大盘点：超分辨率汇总（共32篇）
• CVPR2021 论文大盘点：图像修复汇总（共20篇）
• CVPR2021 论文大盘点：图像去噪汇总（共14篇）
• CVPR2021 论文大盘点：去雾去模糊汇总（共14篇）
• CVPR2021 论文大盘点：图像视频去雨汇总（共10篇）
• CVPR2021 论文大盘点：文本图像汇总（共17篇）
• CVPR2021 论文大盘点：人脸识别汇总（共15篇）
• CVPR2021 论文大盘点：人脸造假检测汇总（共9篇）
• CVPR2021 论文大盘点：图像压缩汇总（共5篇）
• CVPR2021 论文大盘点：遥感与航拍影像汇总（共7篇）
  
  

6.CVPR2020论文下载/代码/解读/直播

• Papers/Codes/Project/PaperReading／Demos/直播分享／论文分享会等
  
• CVPR2020全部论文下载（共1467篇）
  提取码：pun7
  
  
• CVPR2020 论文解读汇总 + 技术直播汇总
  
  

5.CVPR2020论文分方向盘点

• 20.CVPR 2020 论文大盘点-动作检测与动作分割（13篇）
  
• 19.CVPR 2020 论文大盘点-动作识别（21篇）
  
• 18.CVPR 2020 论文大盘点-光流（12篇）
  
• 17.CVPR 2020 论文大盘点-图像与视频检索（16篇）
  
• 16.CVPR 2020 论文大盘点-遥感与航拍影像处理识别（18篇）
  
• 15.CVPR 2020 论文大盘点-图像质量评价（7篇）
  
• 14.CVPR 2020 论文大盘点-图像修复 Inpainting （7篇）
  
• 13.CVPR 2020 论文大盘点-图像增强与图像恢复（22篇）
  
• 12.CVPR 2020 论文大盘点-去雨去雾去模糊（8篇）
  
• 11.CVPR 2020 论文大盘点-医学影像处理识别（19篇）
  
• 10.CVPR 2020 论文大盘点-抠图 Matting （3篇）
  
• 9.CVPR 2020 论文大盘点-图像分割（25篇）
  
• 8.CVPR 2020 论文大盘点-全景分割与视频目标分割（8篇）
  
• 7.CVPR 2020 论文大盘点-超分辨（21篇）
  
• 6.CVPR 2020 论文大盘点-目标检测（64篇）
  
• 5.CVPR 2020 论文大盘点-人脸技术（64篇
  
• 4.CVPR 2020 论文大盘点-目标跟踪（33篇）
  
• 3.CVPR 2020 论文大盘点-文本图像（16篇）
  
• 2.CVPR 2020 论文大盘点-行人检测与重识别（33篇）
  
• 1.CVPR 2020 论文大盘点-实例分割（18篇）
  
  

4.CVPR2019全部论下载/开源代码

全部1294篇

• 全部链接：http://openaccess.thecvf.com/CVPR2019.py
  
• 下载链接:
  链接:https://pan.baidu.com/s/1dhXrWFHeKeJ1kFsKBxQzVg 密码:f53l
• CVPR 2019全部论文开源源码汇总Excel点这里

3.CVPR2019论文分方向盘点

• CVPR 2019 论文大盘点-目标跟踪篇
  
• CVPR 2019 论文大盘点-超分辨率篇
  
• CVPR 2019 论文大盘点-人脸技术篇
  
• CVPR 2019 论文大盘点—目标检测篇
  
• CVPR 2019 论文大盘点—文本图像篇
  
• CVPR2019模型剪枝论文汇总
  
  

2.CVPR2019论文直播分享

• 微软亚研院CVPR2019线下分享会视频回放及PPT下载
• 3/28晚点云分割分享回放
  王鑫龙：联合分割点云中的实例和语义（开源，列表id 27)
  
• 4月18日晚目标检测分享回放
  CMU诸宸辰:基于Anchor-free特征选择模块的单阶目标检测(CVPR2019，列表id 88)
  
• 5月9日晚单目标跟踪分享回放
  张志鹏:基于siamese网络的单目标跟踪(CVPR2019 Oral，列表id 65)
  
• [5月30日晚人脸识别分享回放
  邓健康-CVPR2019:ArcFace 构建高效的人脸识别系统(CVPR2019，列表id 243)：
  
• 6月13日晚三维多人多视角姿态识别分享回放
  董峻廷：多视角下多人三维姿态估计 CVPR2019，列表id 106
  
  

1.CVPR2018/CVPR2017

• CVPR 2018全部论文下载百度云链接：https://pan.baidu.com/s/1bhYzNz2TGijUdfPIdyEGtg
  密码:gyk2
• CVPR 2018论文解读汇总
• CVPR 2017全部论文下载百度云链接：https://pan.baidu.com/s/1p_If8S_AAgnTlZxfzBya2w
  密码:o6tu
• CVPR 2017论文解读集锦
  
  

参考链接

• https://mp.weixin.qq.com/s/YRcajgSTJq_evwtn7ZFo4A
  
• https://github.com/hoya012/CVPR-2019-Paper-Statistics
  
• https://github.com/jonahthelion/cvpr_with_code
  
• https://github.com/amusi/daily-paper-computer-vision
  
  

cvpr2024-paper-code-interpretation's Issues

添加一篇基于骨架的非监督行为识别

CVPR 2020
PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition
论文: https://arxiv.org/abs/1911.12409
代码: https://github.com/shlizee/Predict-Cluster
谢谢！

Pose estimation

Propose to add an accepted paper for CVPR2021

Title: GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation.

arXiv: http://arxiv.org/abs/2102.12145

code: https://github.com/THU-DA-6D-Pose-Group/GDR-Net

Wrong Author List of Paper 121

Thanks very much for creating this archive and listing our paper.

However, author list of Paper 121 RAVEN: A Dataset for Relational and Analogical Visual rEasoNing is wrong.

It should be: Chi Zhang, Feng Gao, Baoxiong Jia, Yixin Zhu, Song-Chun Zhu

41 is same as 391

The question just like the title above

please add our cvpr'19 paper, thanks very much.

Dual Encoding for Zero-Example Video Retrieval
作者：Jianfeng Dong, Xirong Li, Chaoxi Xu, Shouling Ji, Yuan He, Gang Yang and Xun Wang
论文链接：https://arxiv.org/abs/1809.06181 
代码链接：https://github.com/danieljf24/dual_encoding

Please add our code

Please add the code of our CVPR 2021 paper: S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representation

https://github.com/microsoft/S2R-DepthNet

Thanks very much!

模型压缩（二值神经网络）相关文章一篇

模型压缩（二值神经网络）相关文章一篇，已中，感谢添加
论文标题：Forward and Backward Information Retention for Accurate Binary Neural Networks
论文arXiv链接：https://arxiv.org/abs/1909.10788
代码：https://github.com/htqin/IR-Net/

Please add our paper. Thanks.

code & paper: https://github.com/wenguanwang/AGS

#Learning Unsupervised Video Primary Object Segmentation through Visual Attention (CVPR19)

Wenguan Wang, Hongmei Song, Shuyang Zhao, Jianbing Shen, Sanyuan Zhao, Steven Chu Hong Hoi, and Haibin Ling

additional link to the paper: http://www.dabi.temple.edu/~hbling/publication/UVOS-cvpr19.pdf

download Link

2019 CVPR paper download link is invalid, can you share it again? Thank you.

code of VisTR has been released

https://github.com/Epiphqny/VisTR

3D Reconstruction paper

Hi, I saw this CVPR 20 paper with nice github code: https://github.com/autonomousvision/differentiable_volumetric_rendering

Please add a paper

Hi! Could you add our paper to this repo under the category of 三维点云/三维重建? Thanks!

Title: PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation

Paper: https://arxiv.org/abs/2003.14032

Code: https://github.com/edwardzhou130/PolarSeg

Thanks!

Change the Code Link of PAConv

CVPR2021的分类中，点云分类下：
[15] PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds(PAConv：点云上具有动态内核组装的位置自适应卷积)

这篇的code链接请改为：
https://github.com/CVMI-Lab/PAConv

Thanks

添加一篇CVPR2021oral 视频实例分割论文

CVPR2021 oral: End-to-End Video Instance Segmentation with Transformers https://arxiv.org/abs/2011.14503

AANet: Adaptive Aggregation Network for Efficient Stereo Matching

Hi, could you please add our paper to 三维点云/三维重建/三维检测/三维分割/深度估计 category:
AANet: Adaptive Aggregation Network for Efficient Stereo Matching
arXiv: https://arxiv.org/abs/2004.09548
code: https://github.com/haofeixu/aanet
We propose an efficient and accurate architecture for stereo matching without any 3D convs.
Thanks.

Please include our CVPR'21 'TDN' in action recognition

TDN: Temporal Difference Networks for Efficient Action Recognition
Paper: https://arxiv.org/abs/2012.10071
Code: https://github.com/MCG-NJU/TDN

One VOS paper accepted by CVPR 2021

https://arxiv.org/abs/2104.04329, Learning Position and Target Consistency for Memory-based Video Object Segmentation

Add our CVPR paper

Hi, thank you for your collection! Please add our CVPR paper "Generalizable Person Re-identification with Relevance-aware Mixture of Experts". In this paper, we propose a novel method called the relevance-aware mixture of experts (RaMoE) to tackle the problem of domain generalization in person re-identification. Paper link https://arxiv.org/abs/2105.09156.

For Paper id 101

I hope you can note that the code of paper id 101:Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation, is implemented unofficially. Thank you very much.

Please add our CVPR21 Oral paper: DenseCL

Hi,
Could you help add our CVPR21 Oral paper:

• Title: Dense Contrastive Learning for Self-Supervised Visual Pre-Training
• Paper: https://arxiv.org/abs/2011.09157
• Code: https://github.com/WXinlong/DenseCL

Thanks!

Please add our CVPR 2022 paper.

Please add our CVPR 2022 paper in 3D Object Detection: Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving

paper link: https://arxiv.org/abs/2203.02112
code link: https://github.com/revisitq/Pseudo-Stereo-3D

Thanks very much!

Add one accepted CVPR 2021 paper

Topic: 3D object detection, 3D pose estimation, vehicle pose estimation
Title: Exploring intermediate representation for monocular vehicle pose estimation
Code: https://github.com/Nicholasli1995/EgoNet
@extreme-assistant

CVPR2018论文合集的百度云链接过期了

Bag of Tricks for Image Classification with Convolutional Neural Networks

Please add this one: https://arxiv.org/abs/1812.01187
author: Tong He, Zhi Zhang, Hang Zhang, Zhongyue Zhang, Junyuan Xie, Mu Li
code: https://github.com/dmlc/gluon-cv

Thanks!

Image Super-Resolution by Neural Texture Transfer

Add this one.
http://web.eecs.utk.edu/~zzhang61/project_page/SRNTT/SRNTT.html

Please include our CVPR'21 Oral in 'Medical Imaging'

Hi,

Thanks a lot for listing our CVPR'21 oral paper "[26] Discovering Hidden Physics Behind Transport Dynamics". (Paper: https://arxiv.org/abs/2011.12222)
It is a work on perfusion imaging, could you please add it to the ''Medical Imaging' category as well?

Many thanks in advance!

CVPR

5篇CVPR http://cseweb.ucsd.edu/~haosu/#pub
2篇 http://stanford.edu/~rqi/

Directions

How do i use androrat on 9132515506

Please add our CVPR 2021 paper, thanks very much!

The information of our CVPR 2021 paper:

• Title: Transformation Driven Visual Reasoning
• Paper: https://arxiv.org/pdf/2011.13160.pdf
• Code: https://github.com/hughplay/TVR
• Homepage: https://hongxin2019.github.io/TVR/

Thank you very much!

Please add our CVPR2021 paper: DeFCN

Hi,
Could you add our CVPR2021 paper to "Image Object Detection" topic:

Title: End-to-End Object Detection with Fully Convolutional Network
Paper: https://arxiv.org/abs/2012.03544
Code: https://github.com/Megvii-BaseDetection/DeFCN
Zhihu: https://zhuanlan.zhihu.com/p/332281368

Thanks!

The number of paper "Detect-To-Retrieve: Efficient Regional Aggregation for Image Search" github stars is not correct.

As the title said.

Please add our CVPR2021 paper JRGR

Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translation
paper: https://arxiv.org/abs/2103.13660
code: https://github.com/guyii54/JRGR

Please add our CVPR2021 paper || Category: 2D Human Pose Estimation

DCPose: Deep Dual Consecutive Network for Human Pose Estimation
Paper: https://arxiv.org/abs/2103.07254
Code: https://github.com/Pose-Group/DCPose

Please add the code link for our paper

Hi, Thanks for your effort to make this useful git. Please add the code link for our paper

FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism.

The code link is: https://github.com/DC1991/FS_Net

Thanks very much.

Add one CVPR2021 Paper: Cross-Modal Center Loss for 3D Cross-Modal Retrieval

Title: Cross-Modal Center Loss for 3D Cross-Modal Retrieval
Paper Link: https://arxiv.org/abs/2008.03561
Code Link: https://github.com/LongLong-Jing/Cross-Modal-Center-Loss

Paper ID 213

Hi, Thanks for the repo. While this paper is wrongly labeled with "stereo matching" tag. Actually, it proposes architectures for learning correspondence, and can be applied into both "stereo matching" and "optical flow".

Please add our CVPR 2022 paper.

Please help add our CVPR 2022 paper & code in this great repo.

Paper: OpenTAL: Towards Open Set Temporal Action Localization
Code: https://github.com/Cogito2012/OpenTAL

Thank you very much!

An accepted paper for CVPR21

Thanks for adding it into the list~

paper: https://arxiv.org/pdf/2011.12885.pdf
code: https://github.com/implus/GFocalV2
zhihu: https://zhuanlan.zhihu.com/p/313684358

添加一篇CVPR 2020 Oral

PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer
(CVPR 2020 Oral)

paper: https://arxiv.org/abs/1909.06956
code: https://github.com/wtjiang98/PSGAN

New CVPR 2021 Paper

I appreciate it if you can add the following paper

Center-based 3D Object Detection and Tracking

paper: https://arxiv.org/abs/2006.11275
code: https://github.com/tianweiy/CenterPoint

Thanks!

New CVPR paper for adversarial attack(Black-box attack)

Title : Simulating Unknown Target Models for Query-Efficient Black-box Attacks
arXiv: https://arxiv.org/abs/2009.00960 (title will be changed in the revised version)
Code: https://github.com/machanic/MetaSimulator
Intro: We propose a method to train a "Simulator" that can counterfeit any unknown victim models for achieving the query-efficient attack to reducing query complexity of black-box adversarial attacks.

Please add our cvpr'19 paper (0080), thanks very much.

Searching for A Robust Neural Architecture in Four GPU Hours
作者：Xuanyi Dong, Yi Yang
代码链接：https://github.com/D-X-Y/GDAS (will be public soon)

Please add our CVPR paper

Please add our CVPR paper:

Link: https://arxiv.org/abs/2112.05132

Code: https://github.com/Anirudh257/strm

Please add our CVPR 2022 paper.

Please help add our CVPR 2022 paper in this great repo.

paper link: https://arxiv.org/abs/2203.03253

Thanks very much!

Please add our CVPR 2022 paper

Please add our CVPR 2022 paper in 3D Human Pose Estimation/Pose Estimation/Transformer/3D Vision/3D Human Reconstruction:
MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation

paper link: https://arxiv.org/pdf/2111.12707.pdf
code link: https://github.com/Vegetebird/MHFormer

Thanks very much!

CVPR2020论文合集的百度云链接过期了

百度云链接挂了

论文百度云链接挂了

Code link to our CVPR'2021 paper.

Hi, We have already released our code for CVPR2021 paper on 3D point cloud registration: PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency. (paper is already included in this repo)
Paper: https://arxiv.org/abs/2103.05465
Code: https://github.com/XuyangBai/PointDSC

Thanks a lot.

Please add our CVPR 2021 paper

Please add our CVPR 2021 paper in adversarial example: Enhancing the Transferability of Adversarial Attacks through Variance Tuning

paper link: https://arxiv.org/abs/2103.15571
code link: https://github.com/JHL-HUST/VT

Thanks very much!