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

TL;DR

This paper introduces a scalable neural implicit representation for 3D reconstruction that combines multiple local SDFs with overlapping regions, improving accuracy and scalability over traditional single-network methods.

Contribution

It proposes a divide-and-conquer approach modeling scenes as fused local neural SDFs, enhancing reconstruction quality and scalability.

Findings

Achieves high-fidelity surface reconstruction.

Enables scalable scene reconstruction.

Demonstrates effectiveness through extensive experiments.

Abstract

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.