Better Patch Stitching for Parametric Surface Reconstruction
Better patch stitching for parametric surface reconstruction
目录
Motivation
- 对目前的multiple patch based parametric surface representations(atlas),改进patches的
global consistency
(即防止**孔洞和多个patch不正确交叉“jagged/带锯齿**的"的情况) - 典型的缝合问题(1D表示)
Related works:patch-wise representations**
- FoldingNet Foldingnet: Point Cloud Auto-Encoder via Deep Grid Deformation.CVPR2018
第一个基于深度神经网络的工作:学到一个参数化的函数来在3D空间中嵌入一个2D流形 - 后面的工作shifted to ensembles of such learned functions来做patch-wise表征:
- learning (encoder)
- Atlasnet: A papier-mâché approach to learning 3d surface generation. CVPR2018
- Learning elementary structures for 3d shape generation and matching. NeurIPS2019
- Shape reconstruction by learning differentiable surface representations. CVPR2020 这是作者的前作,用正则化来减轻表面的扭曲、重叠
- Tearingnet: Point cloud autoencoder to learn topology-friendly representations. arXiv, 2020.
- optimization (auto-decoder)
- Deep geometric prior for surface reconstruction. CVPR2019
- Meshlet priors for 3d mesh reconstruction. CVPR2020
- 2D output domain
- Deep parametric shape predictions using distance fields. CVPR2020
- 因为连续的patch可以以任意精度采样,因此在拟合的时候可以有很高的精度
- 目前方法的主要缺陷
- 学到的表面高度扭曲、大规模重叠;只能通过适当的regularization正则化来减轻(即作者前一篇工作Shape reconstruction by learning differentiable surface representations)
- 更紧急的问题:individual patches的放置时的global inconsistency,导致surface artifacts,比如孔洞,或者一些多个patch不正确交叉的区域
- 这个问题在meshlet和Deep geometric prior for surface reconstruction. 两篇里有一定程度攻击,但是只在optimization settings,很缓慢,并且在test time还需要几何观测(如带噪声的点云);
- 本篇主要基于learning-based (带encoder) 前作,利用它的低扭曲、低重叠属性,改进patches的global consistency
- learning (encoder)