VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction
This work addresses surface reconstruction issues in 3D Gaussian Splatting for computer vision and graphics applications, offering an incremental improvement over prior methods.
The paper tackled the challenge of extracting high-quality surfaces from 3D Gaussian Splatting representations by proposing a Depth-Normal regularizer and confidence term to improve geometric parameter updates and reduce inconsistencies in normal predictions across views, resulting in better reconstruction quality, competitive appearance, faster training, and 100+ FPS rendering.
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.