本周新出开源计算机视觉代码汇总（含图像超分辨、视频目标分割、行人重识别、点云识别等）

今天汇总了本周新出的计算机视觉开源代码。（有部分已经有git地址但还没上传代码）

共有12份来自前沿计算机视觉研究的代码，CV君数了数，竟然发现其中10份代码所属论文的第一作者是华人！

可见，华人学者在计算机视觉领域异常活跃，而且乐于开源，相信影响力会越来越大。

自适应加权学习的轻量级图像超分辨率

Lightweight Image Super-Resolution with Adaptive Weighted Learning Network

Chaofeng Wang, Zheng Li, Jun Shi

https://github.com/ChaofWang/AWSRN

视频目标分割的时空CNN网络

Spatiotemporal CNN for Video Object Segmentation

Kai Xu, Longyin Wen, Guorong Li, Liefeng Bo, Qingming Huang

https://github.com/longyin880815/STCNN

用于单目深度估计的几何感知对称域适配

Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation

Shanshan Zhao, Huan Fu, Mingming Gong, Dacheng Tao

https://github.com/sshan-zhao/GASDA

样例记忆域适配行人重识别

Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification

Zhun Zhong, Liang Zheng, Zhiming Luo, Shaozi Li, Yi Yang

https://github.com/zhunzhong07/ECN

单目3D人体姿态估计

Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking

Saurabh Sharma, Pavan Teja Varigonda, Prashast Bindal, Abhishek Sharma, Arjun Jain

https://github.com/ssfootball04/generative_pose

非刚体点集配准网络

Non-Rigid Point Set Registration Networks

Lingjing Wang, Jianchun Chen, Xiang Li, Yi Fang

https://github.com/Lingjing324/PR-Net

点云识别

Discrete Rotation Equivariance for Point Cloud Recognition

Jiaxin Li, Yingcai Bi, Gim Hee Lee

https://github.com/lijx10/rot-equ-net

3D点云兴趣点检测

USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds

Jiaxin Li, Gim Hee Lee

https://github.com/lijx10/USIP

高分辨率航空图像中建筑物高效提取网络

ESFNet: Efficient Network for Building Extraction from High-Resolution Aerial Images

Jingbo Lin, Houbing Song, Weipeng Jing

https://github.com/mrluin/ESFNet-Pytorch

跨视图的地理位置定位

Lending Orientation to Neural Networks for Cross-view Geo-localization

Liu Liu, Hongdong Li

https://github.com/Liumouliu/OriCNN

颜色一致性的基准数据集生成器

CroP: Color Constancy Benchmark Dataset Generator

Nikola Banić, Karlo Koščević, Marko Subašić, Sven Lončarić

http://www.fer.unizg.hr/ipg/resources/color_constancy/

少样本学习

Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning

Wenbin Li, Lei Wang, Jinglin Xu, Jing Huo, Yang Gao, Jiebo Luo

https://github.com/WenbinLee/DN4