CVPR2022论文速递（2022.5.17）！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 : 17 May 2022

total number : 6

语义分割/Segmentation - 1 篇

Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization

标题：深度频谱方法：无监督语义分割和定位的令人惊讶的强基线

• 论文/Paper: http://arxiv.org/pdf/2205.07839
• 代码/Code: None

Transformers - - 1 篇

Video Frame Interpolation with Transformer

标题：基于Transformer的视频框架插值

• 论文/Paper: http://arxiv.org/pdf/2205.07230
• 代码/Code: None

视频插帧/Frame Interpolation - 1 篇

Video Frame Interpolation with Transformer

标题：基于Transformer的视频框架插值

• 论文/Paper: http://arxiv.org/pdf/2205.07230
• 代码/Code: None

其他/Other - 4 篇

FvOR: Robust Joint Shape and Pose Optimization for Few-view Object Reconstruction

标题：FVOR：稳健的关节形状和姿势优化，用于重建对象

• 论文/Paper: http://arxiv.org/pdf/2205.07763
• 代码/Code: https://github.com/zhenpeiyang/FvOR/

GLaMa: Joint Spatial and Frequency Loss for General Image Inpainting

标题：GLaMa：用于通用的图像修复的联合空间和频率损失

• 论文/Paper: http://arxiv.org/pdf/2205.07162
• 代码/Code: None

SaiNet: Stereo aware inpainting behind objects with generative networks

标题：SaiNet：立体声意识到具有生成网络的对象后面的涂料

• 论文/Paper: http://arxiv.org/pdf/2205.07014
• 代码/Code: None

RiCS: A 2D Self-Occlusion Map for Harmonizing Volumetric Objects

标题：RiCS：用于协调体积对象的2D自遮挡图

• 论文/Paper: http://arxiv.org/pdf/2205.06975
• 代码/Code: None