Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignment

TL;DR

This paper introduces a level set alignment loss to improve gradient consistency in neural signed distance functions, enhancing their accuracy in reconstructing geometry from point clouds and multi-view images.

Contribution

It proposes a novel level set alignment loss that aligns all level sets to the zero level set, improving gradient consistency and inference accuracy in neural SDFs.

Findings

Significant improvement in SDF inference accuracy across benchmarks

Effective in handling point clouds and multi-view images

Enhances gradient consistency for better geometry reconstruction

Abstract

Neural signed distance functions (SDFs) have shown remarkable capability in representing geometry with details. However, without signed distance supervision, it is still a challenge to infer SDFs from point clouds or multi-view images using neural networks. In this paper, we claim that gradient consistency in the field, indicated by the parallelism of level sets, is the key factor affecting the inference accuracy. Hence, we propose a level set alignment loss to evaluate the parallelism of level sets, which can be minimized to achieve better gradient consistency. Our novelty lies in that we can align all level sets to the zero level set by constraining gradients at queries and their projections on the zero level set in an adaptive way. Our insight is to propagate the zero level set to everywhere in the field through consistent gradients to eliminate uncertainty in the field that is caused by the discreteness of 3D point clouds or the lack of observations from multi-view images. Our proposed loss is a general term which can be used upon different methods to infer SDFs from 3D point clouds and multi-view images. Our numerical and visual comparisons demonstrate that our loss can significantly improve the accuracy of SDFs inferred from point clouds or multi-view images under various benchmarks. Code and data are available at https://github.com/mabaorui/TowardsBetterGradient .