整理：AI算法与图像处理

CVPR2022论文和代码整理：https://github.com/DWCTOD/CVPR2022-Papers-with-Code-Demo

欢迎关注：

Fourier Document Restoration for Robust Document Dewarping and Recognition

• 论文/Paper: http://arxiv.org/pdf/2203.09910

• 代码/Code: None

Learning Affordance Grounding from Exocentric Images

• 论文/Paper: http://arxiv.org/pdf/2203.09905

• 代码/Code: https://github.com/lhc1224/cross-view-affordance-grounding

DTA: Physical Camouflage Attacks using Differentiable Transformation Network

• 论文/Paper: http://arxiv.org/pdf/2203.09831

• 代码/Code: None

Cross-Modal Perceptionist: Can Face Geometry be Gleaned from Voices?

• 论文/Paper: http://arxiv.org/pdf/2203.09824

• 代码/Code: None

Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation

• 论文/Paper: http://arxiv.org/pdf/2203.09811

• 代码/Code: https://github.com/dongxingning/sha-gcl-for-sgg

Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion

• 论文/Paper: http://arxiv.org/pdf/2203.09780

• 代码/Code: None

ContrastMask: Contrastive Learning to Segment Every Thing

• 论文/Paper: http://arxiv.org/pdf/2203.09775

• 代码/Code: None

Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation

• 论文/Paper: http://arxiv.org/pdf/2203.09744

• 代码/Code: https://github.com/lslrh/cpsl

A Dual Weighting Label Assignment Scheme for Object Detection

• 论文/Paper: http://arxiv.org/pdf/2203.09730

• 代码/Code: https://github.com/strongwolf/dw

VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attention

• 论文/Paper: http://arxiv.org/pdf/2203.09704

• 代码/Code: https://github.com/gorilla-lab-scut/vista

Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation

• 论文/Paper: http://arxiv.org/pdf/2203.09653

• 代码/Code: https://github.com/maeve07/rca

Cascade Transformers for End-to-End Person Search

• 论文/Paper: http://arxiv.org/pdf/2203.09642

• 代码/Code: https://github.com/kitware/coat