superpoint+superglue 参考文章

Geometric Loss functions between sampled measures, images and volumes — GeomLoss

https://github.com/jeanfeydy/geomloss

https://github.com/PythonOT/POT

POT: Python Optimal Transport — POT Python Optimal Transport 0.7.0 documentation

superGlue学习_u010949023的博客-优快云博客

superPoint学习_u010949023的博客-优快云博客_superpoint

一种基于注意力机制特征匹配网络SuperGlue：端到端深度学习SLAM的重要里程碑_3D视觉工坊-优快云博客

CVPR论文笔记｜ SuperGlue - 知乎

『论文笔记』SuperGlue - 叠加态的猫 - 博客园

Notes on Optimal Transport

Sinkhorn算法_zsfcg的专栏-优快云博客_sinkhorn

wasserstein 距离（原理+Pytorch 代码实现）_好人就是拉风的博客-优快云博客

令人拍案叫绝的Wasserstein GAN - 知乎

想要算一算Wasserstein距离？这里有一份PyTorch实战

想要算一算Wasserstein距离？这里有一份PyTorch实战 | 机器之心

深度 ｜ 传说中的推土机距离基础，最优传输理论了解一下

【免费】台湾大学李宏毅机器学习课程-6-GAN Lecture 6 (2018) WGAN, EBGAN-优快云讲师的在线视频教程-优快云程序员研修院

GitHub - gpeyre/SinkhornAutoDiff: Toolbox to integrate optimal transport loss functions using automatic differentiation and Sinkhorn's algorithm

SinkhornAutoDiff/sinkhorn_pointcloud.py at master · gpeyre/SinkhornAutoDiff · GitHub

wassdistance/layers.py at master · dfdazac/wassdistance · GitHub

Approximating Wasserstein distances with PyTorch - Daniel Daza

Convolution/Graph Convolution.py at main · CVHuber/Convolution · GitHub

https://github.com/tkipf/pygcn/blob/master/pygcn/layers.py

https://github.com/tkipf/pygcn