GURecon: Learning Detailed 3D Geometric Uncertainties for Neural Surface Reconstruction

TL;DR

GURecon introduces a novel framework that models continuous 3D geometric uncertainty for neural surface reconstruction, improving the assessment of geometric quality without ground truth meshes through geometric consistency and online distillation.

Contribution

It presents a new uncertainty modeling approach for neural surfaces that does not require real geometric supervision and enhances downstream 3D reconstruction tasks.

Findings

Outperforms existing methods in modeling 3D geometric uncertainty

Extends easily to various neural surface representations

Improves incremental reconstruction performance

Abstract

Neural surface representation has demonstrated remarkable success in the areas of novel view synthesis and 3D reconstruction. However, assessing the geometric quality of 3D reconstructions in the absence of ground truth mesh remains a significant challenge, due to its rendering-based optimization process and entangled learning of appearance and geometry with photometric losses. In this paper, we present a novel framework, i.e, GURecon, which establishes a geometric uncertainty field for the neural surface based on geometric consistency. Different from existing methods that rely on rendering-based measurement, GURecon models a continuous 3D uncertainty field for the reconstructed surface, and is learned by an online distillation approach without introducing real geometric information for supervision. Moreover, in order to mitigate the interference of illumination on geometric consistency, a decoupled field is learned and exploited to finetune the uncertainty field. Experiments on various datasets demonstrate the superiority of GURecon in modeling 3D geometric uncertainty, as well as its plug-and-play extension to various neural surface representations and improvement on downstream tasks such as incremental reconstruction. The code and supplementary material are available on the project website: https://zju3dv.github.io/GURecon/.