☪️CVPR2021论文下载：https://pan.baidu.com/share/init?surl=gjfUQlPf73MCk4vM8VbzoA
密码：aicv
欢迎关注公众号：AI算法与图像处理
🌟 CVPR 2022 持续更新最新论文/paper和相应的开源代码/code！
🚗 CVPR 2022 收录列表ID：https://drive.google.com/file/d/15JFhfPboKdUcIH9LdbCMUFmGq_JhaxhC/view
🚗 官网链接：http://cvpr2022.thecvf.com/
B站demo：https://space.bilibili.com/288489574
✋ 注：欢迎各位大佬提交issue，分享CVPR 2022论文/paper和开源项目！共同完善这个项目
往年顶会论文汇总：
CVPR 2022 论文/paper交流群已成立！已经收录的同学，可以添加微信：nvshenj125，请备注：CVPR+姓名+学校/公司名称！一定要根据格式申请，可以拉你进群。
目录（右侧点击可折叠）
- Backbone
- 数据集/Dataset
- NAS
- 多模态 / Multimodal
- Contrastive Learning
- 图神经网络 / Graph Neural Networks
- 胶囊网络 / Capsule Network
- 图像分类 / Image Classification
- 目标检测/Object Detection
- 目标跟踪/Object Tracking
- 语义分割/Segmentation
- 弱监督语义分割/Weakly Supervised Semantic Segmentation
- 医学图像分割
- 视频目标分割/Video Object Segmentation
- 交互式视频目标分割/Interactive Video Object Segmentation
- Visual Transformer
- 深度估计/Depth Estimation
- 人脸识别/Face Recognition
- 人脸检测/Face Detection
- 人脸活体检测/Face Anti-Spoofing
- 人脸年龄估计/Age Estimation
- 人脸表情识别/Facial Expression Recognition
- 人脸属性识别/Facial Attribute Recognition
- 人体姿态估计/Human Pose Estimation
- 6D位姿估计 /6D Pose Estimation
- 手势姿态估计（重建）/Hand Pose Estimation( Hand Mesh Recovery)
- 视频动作检测/Video Action Detection
- 手语翻译/Sign Language Translation
- 3D人体重建
- 行人重识别/Person Re-identification
- 行人搜索/Person Search
- 人群计数 / Crowd Counting
- GAN
- 彩妆迁移 / Color-Pattern Makeup Transfer
- 字体生成 / Font Generation
- 场景文本检测、识别/Scene Text Detection/Recognition
- 图像、视频检索 / Image Retrieval/Video retrieval
- Image Animation
- 抠图/Image Matting
- 超分辨率/Super Resolution
- 图像复原/Image Restoration
- 图像补全/Image Inpainting
- 图像编辑/Image Editing
- 图像拼接/Image stitching
- 图像匹配/Image Matching
- 图像融合/Image Blending
- 图像去雾/Image Dehazing
- 反光去除/Reflection Removal
- 车道线检测/Lane Detection
- 流体重建/Fluid Reconstruction
- 视频插帧/Frame Interpolation
- 3D点云/3D point cloud
- 标签噪声 / Label-Noise
- 对抗样本 Adversarial Examples
【TODO】
GrainSpace: A Large-scale Dataset for Fine-grained and Domain-adaptive Recognition of Cereal Grains
-
论文/Paper：https://arxiv.org/abs/2203.05306
Conditional Prompt Learning for Vision-Language Models
- 论文/Paper：https://arxiv.org/abs/2203.05557
- 代码/Code：https://github.com/KaiyangZhou/CoOp
Motron: Multimodal Probabilistic Human Motion Forecasting
- 论文/Paper：https://arxiv.org/abs/2203.04132
- 代码/Code：
Selective-Supervised Contrastive Learning with Noisy Labels
- 论文/Paper：https://arxiv.org/abs/2203.04181
- 代码/Code：https://github.com/ShikunLi/Sel-CL
Lifelong Graph Learning
- 论文/paper：https://arxiv.org/abs/2009.00647
- 代码/code：https://github.com/wang-chen/LGL
SkinningNet: Two-Stream Graph Convolutional Neural Network for Skinning Prediction of Synthetic Characters
Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer
- 论文/paper：https://arxiv.org/abs/2112.01838 | 主页
- 代码/code：https://github.com/fredzzhang/upt
Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes
Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement
-
论文/Paper：https://arxiv.org/abs/2203.05238
Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability
-
论文/Paper：https://arxiv.org/abs/2203.05180
-
代码/Code：https://github.com/CVMI-Lab/KDEP
DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion
- 论文/Paper：https://arxiv.org/abs/2111.14690
- 代码/Code：https://github.com/DanceTrack/DanceTrack
TCTrack: Temporal Contexts for Aerial Tracking
Iterative Corresponding Geometry: Fusing Region and Depth for Highly Efficient 3D Tracking of Textureless Objects
-
视频/Demo：Youtube
-
论文/Paper：https://arxiv.org/abs/2203.05334
E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation
- 论文/Paper：https://arxiv.org/abs/2203.04074
- 代码/Code：https://github.com/zhang-tao-whu/e2ec
Representation Compensation Networks for Continual Semantic Segmentation
- 论文/Paper：https://arxiv.org/abs/2203.05402
- 代码/Code：https://github.com/zhangchbin/RCIL
Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
- 论文/Paper：https://arxiv.org/abs/2203.03884
- 代码/Code：
ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation
- 论文/paper：https://arxiv.org/abs/2106.05095
- 代码/code：https://github.com/LiheYoung/ST-PlusPlus
Weakly Supervised Semantic Segmentation using Out-of-Distribution Data
- 论文/Paper：https://arxiv.org/abs/2203.03860
- 代码/Code：
Language as Queries for Referring Video Object Segmentation
-
论文/paper：https://arxiv.org/abs/2201.00487
MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation
-
论文/Paper: https://arxiv.org/pdf/2111.12707.pdf
Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut
-
论文/Paper：https://arxiv.org/abs/2202.11539 | 主页
Towards Robust Vision Transformer
-
论文/Paper: https://arxiv.org/abs/2105.07926
-
代码/Code: https://github.com/vtddggg/Robust-Vision-Transformer
OACC-Net: Occlusion-Aware Cost Constructor for Light Field Depth Estimation
- 论文/Paper: https://arxiv.org/pdf/2203.01576.pdf
- 代码/Code: https://github.com/YingqianWang/OACC-Net
Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing
- 论文/Paper: https://arxiv.org/abs/2203.05340
- 代码/Code:
MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation
-
论文/Paper: https://arxiv.org/pdf/2111.12707.pdf
End-to-End Semi-Supervised Learning for Video Action Detection
- 论文/Paper：https://arxiv.org/abs/2203.04251
- 代码/Code：
A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation
- 论文/Paper：https://arxiv.org/abs/2203.04287
- 代码/Code：
MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation
-
论文/Paper: https://arxiv.org/pdf/2111.12707.pdf
FlexIT: Towards Flexible Semantic Image Translation
-
论文/paper：https://arxiv.org/abs/2203.04705
-
代码/code：
GAN-Supervised Dense Visual Alignment
-
论文/paper：https://arxiv.org/abs/2112.05143
HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing
-
论文/paper：https://arxiv.org/abs/2111.15666 | 主页
Reflash Dropout in Image Super-Resolution
-
论文/Paper：https://arxiv.org/pdf/2112.12089.pdf
-
代码/Code：https://github.com/Xiangtaokong/Reflash-Dropout-in-Image-Super-Resolution
Bridging Global Context Interactions for High-Fidelity Image Completion
-
论文/Paper：https://arxiv.org/abs/2104.00845
Deep Rectangling for Image Stitching: A Learning Baseline
Rethinking Efficient Lane Detection via Curve Modeling
ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotation
- 论文/Paper：https://arxiv.org/abs/2203.03888
- 代码/Code：
Contrastive Boundary Learning for Point Cloud Segmentation
Shape-invariant 3D Adversarial Point Clouds
- 论文/Paper：https://arxiv.org/abs/2203.04041
- 代码/Code：https://github.com/shikiw/SI-Adv
DINE: Domain Adaptation from Single and Multiple Black-box Predictors
-
论文/Paper：https://arxiv.org/abs/2104.01539
It's About Time: Analog clock Reading in the Wild
Neural Face Identification in a 2D Wireframe Projection of a Manifold Object
- 论文/Paper：https://arxiv.org/abs/2203.04229 | 主页
- 代码/Code：https://github.com/manycore-research/faceformer
Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences
TeachAugment: Data Augmentation Optimization Using Teacher Knowledge
UKPGAN: Unsupervised KeyPoint GANeration
-
论文/Paper：
DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos
- 论文/Paper：https://arxiv.org/abs/2203.03996
- 代码/Code：
Generative Cooperative Learning for Unsupervised Video Anomaly Detection
- 论文/Paper：https://arxiv.org/abs/2203.03962
- 代码/Code：
Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon
- 论文/Paper：https://arxiv.org/abs/2203.03818
- 代码/Code：
Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild
On Generalizing Beyond Domains in Cross-Domain Continual Learning
- 论文/Paper：https://arxiv.org/abs/2203.03970
- 代码/Code：
Generating 3D Bio-Printable Patches Using Wound Segmentation and Reconstruction to Treat Diabetic Foot Ulcers
- 论文/Paper：https://arxiv.org/abs/2203.03814
- 代码/Code：
What Matters For Meta-Learning Vision Regression Tasks?
- 论文/Paper：https://arxiv.org/abs/2203.04905
- 代码/Code：
How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting
-
论文/Paper：https://arxiv.org/abs/2203.04781
-
代码/Code：
ChiTransformer:Towards Reliable Stereo from Cues
-
论文/Paper：https://arxiv.org/abs/2203.04554
-
代码/Code：
Dynamic Dual-Output Diffusion Models
-
论文/Paper：https://arxiv.org/abs/2203.04304
-
代码/Code：
Spatial Commonsense Graph for Object Localisation in Partial Scenes
-
论文/Paper：https://arxiv.org/abs/2203.05380
-
代码/Code：https://fgiuliari.github.io/projects/SpatialCommonsenseGraph/
Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack
Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity
-
论文/Paper：https://arxiv.org/abs/2203.05151
-
代码/Code：
-
视频/Demo：
-
解读：
-
论文/Paper：
-
代码/Code：
参考：
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent