A Neural Galerkin Solver for Accurate Surface Reconstruction

Author:

Huang Jiahui1,Chen Hao-Xiang1,Hu Shi-Min1

Affiliation:

1. Tsinghua University, China

Abstract

To reconstruct meshes from the widely-available 3D point cloud data, implicit shape representation is among the primary choices as an intermediate form due to its superior representation power and robustness in topological optimizations. Although different parameterizations of the implicit fields have been explored to model the underlying geometry, there is no explicit mechanism to ensure the fitting tightness of the surface to the input. We present in response, NeuralGalerkin, a neural Galerkin-method-based solver designed for reconstructing highly-accurate surfaces from the input point clouds. NeuralGalerkin internally discretizes the target implicit field as a linear combination of a set of spatially-varying basis functions inferred by an adaptive sparse convolution neural network. It then solves differentiably for a variational problem that incorporates both positional and normal constraints from the data in closed form within a single forward pass, highly respecting the raw input points. The reconstructed surface extracted from the implicit interpolants is hence very accurate and incorporates useful inductive biases benefiting from the training data. Extensive evaluations on various datasets demonstrate our method's promising reconstruction performance and scalability.

Funder

Tsinghua-Tencent Joint Laboratory for Internet Innovation Technology

Research Grant of Beijing Higher In- stitution Engineering Research Center

National Key R&D Program of China

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Graphics and Computer-Aided Design

Reference72 articles.

1. Neural jacobian fields

2. SAL: Sign Agnostic Learning of Shapes From Raw Data

3. Matan Atzmon and Yaron Lipman . 2020 b. SALD: Sign Agnostic Learning with Derivatives. In Int. Conf. Learning Representations. Matan Atzmon and Yaron Lipman. 2020b. SALD: Sign Agnostic Learning with Derivatives. In Int. Conf. Learning Representations.

4. Dejan Azinović , Ricardo Martin-Brualla , Dan B Goldman , Matthias Nießner , and Justus Thies . 2021. Neural RGB-D surface reconstruction. arXiv preprint arXiv:2104.04532 ( 2021 ). Dejan Azinović, Ricardo Martin-Brualla, Dan B Goldman, Matthias Nießner, and Justus Thies. 2021. Neural RGB-D surface reconstruction. arXiv preprint arXiv:2104.04532 (2021).

5. SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences

Cited by 13 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Diffusing Colors: Image Colorization with Text Guided Diffusion;SIGGRAPH Asia 2023 Conference Papers;2023-12-10

2. VQ-InfraTrans: A Unified Framework for RGB-IR Translation with Hybrid Transformer;Remote Sensing;2023-12-07

3. Neural-Singular-Hessian: Implicit Neural Representation of Unoriented Point Clouds by Enforcing Singular Hessian;ACM Transactions on Graphics;2023-12-05

4. YOGA: Yet Another Geometry-based Point Cloud Compressor;Proceedings of the 31st ACM International Conference on Multimedia;2023-10-26

5. Magenta Green Screen: Spectrally Multiplexed Alpha Matting with Deep Colorization;Proceedings of the Digital Production Symposium;2023-08-05

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3