Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction

TL;DR

This paper introduces a geometry-consistent neural implicit surface learning method for multi-view reconstruction that explicitly incorporates multi-view geometry constraints, resulting in more accurate and reliable surface reconstructions.

Contribution

It bridges the gap between volume rendering and SDF modeling by explicitly optimizing the zero-level set with multi-view geometry constraints, improving reconstruction quality.

Findings

Outperforms state-of-the-art methods in complex structures

Achieves high-quality reconstructions in diverse scenarios

Effectively integrates multi-view geometry constraints

Abstract

Recently, neural implicit surfaces learning by volume rendering has become popular for multi-view reconstruction. However, one key challenge remains: existing approaches lack explicit multi-view geometry constraints, hence usually fail to generate geometry consistent surface reconstruction. To address this challenge, we propose geometry-consistent neural implicit surfaces learning for multi-view reconstruction. We theoretically analyze that there exists a gap between the volume rendering integral and point-based signed distance function (SDF) modeling. To bridge this gap, we directly locate the zero-level set of SDF networks and explicitly perform multi-view geometry optimization by leveraging the sparse geometry from structure from motion (SFM) and photometric consistency in multi-view stereo. This makes our SDF optimization unbiased and allows the multi-view geometry constraints to focus on the true surface optimization. Extensive experiments show that our proposed method achieves high-quality surface reconstruction in both complex thin structures and large smooth regions, thus outperforming the state-of-the-arts by a large margin.