CVPR2022论文速递（2022.4.25）！共9篇！Transformer+多模态用于食品检索

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 : 25 Apr 2022

total number : 9

语义分割/Segmentation - 2 篇

Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation

标题：动态原型卷积网络，用于少样本语义分割

• 论文/Paper: http://arxiv.org/pdf/2204.10638
• 代码/Code: None

Interactive Segmentation and Visualization for Tiny Objects in Multi-megapixel Images

标题：多兆像素图像中微小对象的交互式分割和可视化

• 论文/Paper: http://arxiv.org/pdf/2204.10356
• 代码/Code: https://github.com/cy-xu/cosmic-conn

人脸相关 / Face - 1 篇

JIFF: Jointly-aligned Implicit Face Function for High Quality Single View Clothed Human Reconstruction

标题：JIFF：高质量单视角人体重建的共同结合的人脸隐函数

• 论文/Paper: http://arxiv.org/pdf/2204.10549
• 代码/Code: None

点云/Point Clouds - 1 篇

Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors

标题：用地表先验的稀疏点云重建表面

• 论文/Paper: http://arxiv.org/pdf/2204.10603
• 代码/Code: https://github.com/mabaorui/onsurfaceprior

其他/Other - 5 篇

Exposure Correction Model to Enhance Image Quality

标题：曝光校正模型提高图像质量

• 论文/Paper: http://arxiv.org/pdf/2204.10648
• 代码/Code: https://github.com/yamand16/exposurecorrection

Spacing Loss for Discovering Novel Categories

标题：发现新型类别的Spacing Loss

• 论文/Paper: http://arxiv.org/pdf/2204.10595
• 代码/Code: https://github.com/josephkj/awesome-novel-class-discovery

DiRA: Discriminative, Restorative, and Adversarial Learning for Self-supervised Medical Image Analysis

标题：Dira：自我监督医学图像分析的歧视性，恢复性和对抗性学习

• 论文/Paper: http://arxiv.org/pdf/2204.10437
• 代码/Code: https://github.com/jlianglab/dira

The 6th AI City Challenge

标题：第6届AI城市挑战

• 论文/Paper: http://arxiv.org/pdf/2204.10380
• 代码/Code: None

Contrastive Test-Time Adaptation

标题：对比度测试时间适应

• 论文/Paper: http://arxiv.org/pdf/2204.10377
• 代码/Code: None