目录

目录

Shape Reconstruction by Learning Differentiable Surface Representations


Shape reconstruction by learning differentiable surface representations

Motivation

  • 目前有一些学习an ensumble of Parametric表征的方法
    • 但是这些方法并没有控制表面patch的变形,因此并不能阻止patches彼此重叠或者折叠成一个点、一条线
    • 这种情况下,计算表面法向量就会变得困难、不可靠
  • 本篇提出 在训练时,开发深度神经网络的天生的可微性
    • 来利用表面的微分属性去阻止patch折叠、显著减少互相重叠
    • 并且这让我们可以可靠地计算表面法向量、曲率等
  • https://longtimenohack.com/posts/paper_reading/2020cvpr_bednarik_shape/image-20201224164231425.png
  • Learning to Reconstruct Texture-Less Deformable Surfaces. 3DV2018
  • Marr Revisited: 2D-3D Model Alignment via Surface Normal Prediction. CVPR2016
  • A Two-Stream Network for Fast and Accurate 3D Cloth Draping. ICCV2019

overview

  • https://longtimenohack.com/posts/paper_reading/2020cvpr_bednarik_shape/image-20201224193837533.png

results

  • 主要对比基线就是atlasNet
  • Pointcloud Autoencoding (PCAE)
    https://longtimenohack.com/posts/paper_reading/2020cvpr_bednarik_shape/image-20201224175724685.png
  • single view reconstruction (SVR) 单目重建
    https://longtimenohack.com/posts/paper_reading/2020cvpr_bednarik_shape/image-20201224175853915.png