Deep geometric prior for surface reconstruction
<Deep geometric prior>
Deep geometric prior for surface reconstruction目录
Motivation
- 首先把输入点云分成若干个重叠的部分，然后用MLP流形学习每个部分；
- 每个local流形学习用
2-Wasserstein loss/EMD loss；
并在所有流形之间保证consistency 
<Deep geometric prior>
Deep geometric prior for surface reconstruction2-Wasserstein loss / EMD loss；
