Photometric Regularization for 3D Gaussian Splatting in Multi-View Surface Projection

Abstract

3D surface representation from multi-view photometric stereo (MVPS) remains a challenging task due to accumulated errors and geometric inconsistencies in conventional fusion-based methods. While 3D Gaussian Splatting (3DGS) enables real-time rendering, its explicit point-based representation struggles to preserve fine geometric details when directly applied to MVPS. To address this limitation, we propose PS-GS, a novel photometric-regularized Gaussian splatting framework that integrates surface normal priors to enhance multi-view surface projection. Specifically, PS-GS introduces three regularization strategies: (1) normal-guided initialization, which aligns Gaussian splats with photometric surface normals; (2) adaptive splat cloning, which dynamically adjusts point density in regions with high normal variation to improve local detail preservation; and (3) visibility-aware occlusion handling, which ensures geometric consistency across multi-view projections. Unlike NeRF-based MVPS methods, our approach does not rely on implicit volumetric representations and instead optimizes explicit surface projections, achieving efficient and artifact-free rendering. Experimental results on the DiLiGenT-MV benchmark demonstrate that PS-GS significantly improves 2D photometric fidelity, achieving a 2.18 dB PSNR gain over NeRF-based MVPS methods while maintaining around 150× faster rendering efficiency. Additionally, our normal-guided splatting enhances view-consistent normal alignment, reducing artifacts in challenging regions. Although PS-GS does not perform full 3D mesh reconstruction or relighting, its efficient rendering and surface-aware regularization make it a promising approach for real-time multi-view image synthesis in MVPS applications.