Multi-scale hash encoding based neural geometry representation

IF 17.3 3区计算机科学 Q1 COMPUTER SCIENCE, SOFTWARE ENGINEERING

Computational Visual Media Pub Date : 2024-03-22 DOI:10.1007/s41095-023-0340-x

{"title":"Multi-scale hash encoding based neural geometry representation","authors":"","doi":"10.1007/s41095-023-0340-x","DOIUrl":null,"url":null,"abstract":"<h3>Abstract</h3> <p>Recently, neural implicit function-based representation has attracted more and more attention, and has been widely used to represent surfaces using differentiable neural networks. However, surface reconstruction from point clouds or multi-view images using existing neural geometry representations still suffer from slow computation and poor accuracy. To alleviate these issues, we propose a multi-scale hash encoding-based neural geometry representation which effectively and efficiently represents the surface as a signed distance field. Our novel neural network structure carefully combines low-frequency Fourier position encoding with multi-scale hash encoding. The initialization of the geometry network and geometry features of the rendering module are accordingly redesigned. Our experiments demonstrate that the proposed representation is at least 10 times faster for reconstructing point clouds with millions of points. It also significantly improves speed and accuracy of multi-view reconstruction. Our code and models are available at https://github.com/Dengzhi-USTC/Neural-Geometry-Reconstruction. <span> <span> <img alt=\"\" src=\"https://static-content.springer.com/image/MediaObjects/41095_2023_340_Fig1_HTML.jpg\"/> </span> </span></p>","PeriodicalId":37301,"journal":{"name":"Computational Visual Media","volume":"8 1","pages":""},"PeriodicalIF":17.3000,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computational Visual Media","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s41095-023-0340-x","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}

引用次数: 0

Abstract

Recently, neural implicit function-based representation has attracted more and more attention, and has been widely used to represent surfaces using differentiable neural networks. However, surface reconstruction from point clouds or multi-view images using existing neural geometry representations still suffer from slow computation and poor accuracy. To alleviate these issues, we propose a multi-scale hash encoding-based neural geometry representation which effectively and efficiently represents the surface as a signed distance field. Our novel neural network structure carefully combines low-frequency Fourier position encoding with multi-scale hash encoding. The initialization of the geometry network and geometry features of the rendering module are accordingly redesigned. Our experiments demonstrate that the proposed representation is at least 10 times faster for reconstructing point clouds with millions of points. It also significantly improves speed and accuracy of multi-view reconstruction. Our code and models are available at https://github.com/Dengzhi-USTC/Neural-Geometry-Reconstruction. Abstract Image

查看原文本刊更多论文

基于神经几何表示的多尺度哈希编码

摘要近年来，基于神经隐函数的表示法越来越受到关注，并被广泛用于利用可微神经网络表示曲面。然而，使用现有的神经几何表示法从点云或多视角图像中重建曲面仍然存在计算速度慢、精度低的问题。为了缓解这些问题，我们提出了一种基于多尺度哈希编码的神经几何表示法，它能有效且高效地将曲面表示为有符号的距离场。我们新颖的神经网络结构将低频傅立叶位置编码与多尺度哈希编码巧妙地结合在一起。几何网络的初始化和渲染模块的几何特征也相应进行了重新设计。我们的实验证明，在重建数百万个点的点云时，所提出的表示方法至少快 10 倍。它还大大提高了多视角重建的速度和精度。我们的代码和模型可在 https://github.com/Dengzhi-USTC/Neural-Geometry-Reconstruction 上查阅。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Computational Visual Media Computer Science-Computer Graphics and Computer-Aided Design

CiteScore

16.90

自引率

5.80%

发文量

243

审稿时长

6 weeks

期刊介绍： Computational Visual Media is a peer-reviewed open access journal. It publishes original high-quality research papers and significant review articles on novel ideas, methods, and systems relevant to visual media. Computational Visual Media publishes articles that focus on, but are not limited to, the following areas: • Editing and composition of visual media • Geometric computing for images and video • Geometry modeling and processing • Machine learning for visual media • Physically based animation • Realistic rendering • Recognition and understanding of visual media • Visual computing for robotics • Visualization and visual analytics Other interdisciplinary research into visual media that combines aspects of computer graphics, computer vision, image and video processing, geometric computing, and machine learning is also within the journal''s scope. This is an open access journal, published quarterly by Tsinghua University Press and Springer. The open access fees (article-processing charges) are fully sponsored by Tsinghua University, China. Authors can publish in the journal without any additional charges.