BriefGPT.xyz
Aug, 2021
学习符号距离场进行多视角表面重建
Learning Signed Distance Field for Multi-view Surface Reconstruction
HTML
PDF
Jingyang Zhang, Yao Yao, Long Quan
TL;DR
本研究提出了一种基于神经隐式表达并结合立体匹配和特征保持的新型表面重建框架,使用有符号距离场和表面光场直接表示场景几何及外观,并通过优化多视角特征一致性和渲染图像的保真度来精细化表示几何形状,提高了复杂场景拓扑的重建鲁棒性,实验结果表明相较于现有最优方法,本方法在无需输入蒙版的广阔场景网格重建上具有更佳的表现。
Abstract
Recent works on
implicit neural representations
have shown promising results for
multi-view surface reconstruction
. However, most approaches are limited to relatively simple geometries and usually require clean o
→