Photometric regularization for 3D gaussian splatting in multi-view surface projection

Ju, Yakun, Zhao, Yuying, Xiao, Jun, Zhang, Cong, Jiang, Zheheng, Zhou, Huiyu, Zhou, Wei, Yu, Hui and Dong, Junyu 2025. Photometric regularization for 3D gaussian splatting in multi-view surface projection. IEEE Journal of Selected Topics in Signal Processing 10.1109/jstsp.2025.3617861

Full text not available from this repository.

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 PSGS, a novel photometric-regularized Gaussian splatting framework that integrates surface normal priors to enhance multiview 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 NeRFbased 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.

Item Type:	Article
Date Type:	Published Online
Status:	In Press
Schools:	Schools > Computer Science & Informatics
Additional Information:	License information from Publisher: LICENSE 1: URL: https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html, Start Date: 2025-01-01
Publisher:	Institute of Electrical and Electronics Engineers
ISSN:	1932-4553
Last Modified:	21 Oct 2025 09:30
URI:	https://orca.cardiff.ac.uk/id/eprint/181791

Actions (repository staff only)

Edit Item