CVPR2022论文速递（2022.4.14）！共6篇！

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

Updated on : 14 Apr 2022

total number : 6

语义分割/Segmentation - 1 篇

Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity

标题：开放世界实例分割：从学到的成对样本相似性中利用伪 Ground Truth

• 论文/Paper: http://arxiv.org/pdf/2204.06107
• 代码/Code: None

其他/Other - 5 篇

Recognition of Freely Selected Keypoints on Human Limbs

标题：在人肢上识别自由选择的关键点

• 论文/Paper: http://arxiv.org/pdf/2204.06326
• 代码/Code: None

Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesis

标题：用于3D感知图像合成的多视图一致生成的对抗网络

• 论文/Paper: http://arxiv.org/pdf/2204.06307
• 代码/Code: None

3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection

标题：3D-SPS：通过参考点逐行选择单级3D视觉Grounding

• 论文/Paper: http://arxiv.org/pdf/2204.06272
• 代码/Code: None

Defensive Patches for Robust Recognition in the Physical World

标题：在物理世界中为强大的识别防御补丁

• 论文/Paper: http://arxiv.org/pdf/2204.06213
• 代码/Code: https://github.com/nlsde-safety-team/DefensivePatch

COAP: Compositional Articulated Occupancy of People

标题：COAP：组成铰接式Occupancy的人

• 论文/Paper: http://arxiv.org/pdf/2204.06184
• 代码/Code: https://neuralbodies.github.io/COAP/index.html