Multi-scale hash encoding based neural geometry representation  

作　　者：Zhi Deng Haoyao Xiao Yining Lang Hao Feng Juyong Zhang 

机构地区：[1]School of Mathematical Sciences,University of Science and Technology of China,Hefei 230026,China [2]Alibaba Artificial Intelligence Governance Laboratory,Alibaba Group,Hangzhou 310017,China

出　　处：《Computational Visual Media》2024年第3期453-470,共18页计算可视媒体（英文版）

基　　金：supported by the National Natural Science Foundation of China(Nos.62122071 and 62272433);the Fundamental Research Funds for the Central Universities(No.WK3470000021);the Alibaba Innovation Research Program(AIR).

摘　　要：Recently, neural implicit function-basedrepresentation has attracted more and more attention,and has been widely used to represent surfacesusing differentiable neural networks. However, surfacereconstruction from point clouds or multi-view imagesusing existing neural geometry representations stillsuffer from slow computation and poor accuracy. Toalleviate these issues, we propose a multi-scale hashencoding-based neural geometry representation whicheffectively and efficiently represents the surface asa signed distance field. Our novel neural networkstructure carefully combines low-frequency Fourierposition encoding with multi-scale hash encoding. Theinitialization of the geometry network and geometryfeatures of the rendering module are accordinglyredesigned. Our experiments demonstrate that theproposed representation is at least 10 times faster forreconstructing point clouds with millions of points.It also significantly improves speed and accuracyof multi-view reconstruction. Our code and modelsare available at https://github.com/Dengzhi-USTC/Neural-Geometry-Reconstruction.

关 键 词：neural geometry representation hash encoding point cloud reconstruction multi-view reconstruction 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程]