Scalable and High-Quality Neural Implicit Representation for 3D Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Leyuan, Deng, Bailin, Zhang, Juyong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910786608168960
author Yang, Leyuan
Deng, Bailin
Zhang, Juyong
author_facet Yang, Leyuan
Deng, Bailin
Zhang, Juyong
contents Various SDF-based neural implicit surface reconstruction methods have been proposed recently, and have demonstrated remarkable modeling capabilities. However, due to the global nature and limited representation ability of a single network, existing methods still suffer from many drawbacks, such as limited accuracy and scale of the reconstruction. In this paper, we propose a versatile, scalable and high-quality neural implicit representation to address these issues. We integrate a divide-and-conquer approach into the neural SDF-based reconstruction. Specifically, we model the object or scene as a fusion of multiple independent local neural SDFs with overlapping regions. The construction of our representation involves three key steps: (1) constructing the distribution and overlap relationship of the local radiance fields based on object structure or data distribution, (2) relative pose registration for adjacent local SDFs, and (3) SDF blending. Thanks to the independent representation of each local region, our approach can not only achieve high-fidelity surface reconstruction, but also enable scalable scene reconstruction. Extensive experimental results demonstrate the effectiveness and practicality of our proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2501_08577
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Scalable and High-Quality Neural Implicit Representation for 3D Reconstruction
Yang, Leyuan
Deng, Bailin
Zhang, Juyong
Computer Vision and Pattern Recognition
Graphics
Various SDF-based neural implicit surface reconstruction methods have been proposed recently, and have demonstrated remarkable modeling capabilities. However, due to the global nature and limited representation ability of a single network, existing methods still suffer from many drawbacks, such as limited accuracy and scale of the reconstruction. In this paper, we propose a versatile, scalable and high-quality neural implicit representation to address these issues. We integrate a divide-and-conquer approach into the neural SDF-based reconstruction. Specifically, we model the object or scene as a fusion of multiple independent local neural SDFs with overlapping regions. The construction of our representation involves three key steps: (1) constructing the distribution and overlap relationship of the local radiance fields based on object structure or data distribution, (2) relative pose registration for adjacent local SDFs, and (3) SDF blending. Thanks to the independent representation of each local region, our approach can not only achieve high-fidelity surface reconstruction, but also enable scalable scene reconstruction. Extensive experimental results demonstrate the effectiveness and practicality of our proposed method.
title Scalable and High-Quality Neural Implicit Representation for 3D Reconstruction
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2501.08577