☪️CVPR2022论文下载：添加微信: nvshenj125, 备注 CVPR 2022 即可获取全部论文pdf
☪️福利 注册即可领取 200 块计算资源 : https://www.bkunyun.com/wap/console?source=aistudy 使用说明
欢迎关注公众号：AI算法与图像处理
🌟 CVPR 2023 持续更新最新论文/paper和相应的开源代码/code！
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 2023 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
- Knowledge Distillation
- 多模态 / Multimodal
- 对比学习/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
- 轨迹预测/Trajectory Prediction
- 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
- 人脸编辑/Facial Editing
- 人脸重建/Face Reconstruction
- 换脸/Face Swap
- 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
- 图像去噪/Image Denoising
- 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
- 图像压缩/Image Compression
- 反光去除/Reflection Removal
- 车道线检测/Lane Detection
- 自动驾驶 / Autonomous Driving
- 流体重建/Fluid Reconstruction
- 场景重建 / Scene Reconstruction
- 视频插帧/Frame Interpolation
- 视频超分 / Video Super-Resolution
- 3D点云/3D point cloud
- 标签噪声 / Label-Noise
- 对抗样本/Adversarial Examples
- 其他/Other
Paper title: Generic-to-Specific Distillation of Masked Autoencoders
- 论文/Paper: https://arxiv.org/abs/2302.14771
- 代码/Code: https://github.com/pengzhiliang/G2SD
PolyFormer: Referring Image Segmentation as Sequential Polygon Generation
- 论文/Paper: https://arxiv.org/abs/2302.14771
- 代码/Code: None
Multimodal Industrial Anomaly Detection via Hybrid Fusion
- 论文/Paper: http://arxiv.org/pdf/2303.00601
- 代码/Code: https://github.com/nomewang/m3dm
Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision
- 论文/Paper: http://arxiv.org/pdf/2303.00462
- 代码/Code: https://github.com/toytiny/cmflow
IPCC-TP: Utilizing Incremental Pearson Correlation Coefficient for Joint Multi-Agent Trajectory Prediction
- 论文/Paper: http://arxiv.org/pdf/2303.00575
- 代码/Code: None
Interactive Segmentation as Gaussian Process Classification
- 论文/Paper: http://arxiv.org/pdf/2302.14578
- 代码/Code: None
Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation
- 论文/Paper: http://arxiv.org/pdf/2302.14250
- 代码/Code: None
PolyFormer: Referring Image Segmentation as Sequential Polygon Generation
- 论文/Paper: https://arxiv.org/abs/2302.14771
- 代码/Code: None
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution
- 论文/Paper: http://arxiv.org/pdf/2303.00246
- 代码/Code: None
Mask3D: Pre-training 2D Vision Transformers by Learning Masked 3D Priors
- 论文/Paper: http://arxiv.org/pdf/2302.14746
- 代码/Code: None
ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformer
- 论文/Paper: http://arxiv.org/pdf/2302.14435
- 代码/Code: https://github.com/I2-Multimedia-Lab/ProxyFormer.
ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformer
- 论文/Paper: http://arxiv.org/pdf/2302.14435
- 代码/Code: https://github.com/I2-Multimedia-Lab/ProxyFormer.
Im2Hands: Learning Attentive Implicit Representation of Interacting Two-Hand Shapes
- 论文/Paper: http://arxiv.org/pdf/2302.14348
- 代码/Code: https://github.com/jyunlee/Im2Hands
Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation
- 论文/Paper: http://arxiv.org/pdf/2303.00440
- 代码/Code: https://github.com/MCG-NJU/EMA-VFI
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution
- 论文/Paper: http://arxiv.org/pdf/2303.00246
- 代码/Code: None
PA&DA: Jointly Sampling PAth and DAta for Consistent NAS
- 论文/Paper: http://arxiv.org/pdf/2302.14772
- 代码/Code: https://github.com/ShunLu91/PA-DA
Generic-to-Specific Distillation of Masked Autoencoders
- 论文/Paper: http://arxiv.org/pdf/2302.14771
- 代码/Code: https://github.com/pengzhiliang/G2SD.
Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger
- 论文/Paper: http://arxiv.org/pdf/2302.14677
- 代码/Code: None
Turning a CLIP Model into a Scene Text Detector
- 论文/Paper: http://arxiv.org/pdf/2302.14338
- 代码/Code: None
Adversarial Attack with Raindrops
- 论文/Paper: http://arxiv.org/pdf/2302.14267
- 代码/Code: None
Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning
- 论文/Paper: http://arxiv.org/pdf/2302.14115
- 代码/Code: None
DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks
- 论文/Paper: http://arxiv.org/pdf/2302.14685
- 代码/Code: None
Neural Video Compression with Diverse Contexts
- 论文/Paper: http://arxiv.org/pdf/2302.14402
- 代码/Code: https://github.com/microsoft/DCVC
Learning to Retain while Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation
- 论文/Paper: http://arxiv.org/pdf/2302.14290
- 代码/Code: None
Efficient and Explicit Modelling of Image Hierarchies for Image Restoration
- 论文/Paper: http://arxiv.org/pdf/2303.00748
- 代码/Code: https://github.com/ofsoundof/grl-image-restoration
Quality-aware Pre-trained Models for Blind Image Quality Assessment
- 论文/Paper: http://arxiv.org/pdf/2303.00521
- 代码/Code: None
Renderable Neural Radiance Map for Visual Navigation
- 论文/Paper: http://arxiv.org/pdf/2303.00304
- 代码/Code: None
Single Image Backdoor Inversion via Robust Smoothed Classifiers
- 论文/Paper: http://arxiv.org/pdf/2303.00215
- 代码/Code: https://github.com/locuslab/smoothinv
Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training
- 论文/Paper: http://arxiv.org/pdf/2303.00040
- 代码/Code: None
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent