VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction

TL;DR

This paper introduces VCR-GauS, a regularizer for Gaussian surface reconstruction that couples normals with geometric parameters and mitigates multi-view inconsistencies, resulting in improved quality and efficiency.

Contribution

The paper proposes a novel Depth-Normal regularizer with a confidence term and a densification strategy for better Gaussian surface reconstruction.

Findings

Achieves higher reconstruction quality than Gaussian baselines.

Maintains competitive appearance quality with faster training and rendering speeds.

Provides a robust method for multi-view normal consistency.

Abstract

Although 3D Gaussian Splatting has been widely studied because of its realistic and efficient novel-view synthesis, it is still challenging to extract a high-quality surface from the point-based representation. Previous works improve the surface by incorporating geometric priors from the off-the-shelf normal estimator. However, there are two main limitations: 1) Supervising normals rendered from 3D Gaussians effectively updates the rotation parameter but is less effective for other geometric parameters; 2) The inconsistency of predicted normal maps across multiple views may lead to severe reconstruction artifacts. In this paper, we propose a Depth-Normal regularizer that directly couples normal with other geometric parameters, leading to full updates of the geometric parameters from normal regularization. We further propose a confidence term to mitigate inconsistencies of normal predictions across multiple views. Moreover, we also introduce a densification and splitting strategy to regularize the size and distribution of 3D Gaussians for more accurate surface modeling. Compared with Gaussian-based baselines, experiments show that our approach obtains better reconstruction quality and maintains competitive appearance quality at faster training speed and 100+ FPS rendering.