PS-GS: Gaussian Splatting for Multi-View Photometric Stereo

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Yixiao, Liang, Bin, Guo, Hanzhi, Cheng, Yongqing, Zhao, Jiayi, Weng, Dongdong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916861517496320
author Chen, Yixiao
Liang, Bin
Guo, Hanzhi
Cheng, Yongqing
Zhao, Jiayi
Weng, Dongdong
author_facet Chen, Yixiao
Liang, Bin
Guo, Hanzhi
Cheng, Yongqing
Zhao, Jiayi
Weng, Dongdong
contents Integrating inverse rendering with multi-view photometric stereo (MVPS) yields more accurate 3D reconstructions than the inverse rendering approaches that rely on fixed environment illumination. However, efficient inverse rendering with MVPS remains challenging. To fill this gap, we introduce the Gaussian Splatting for Multi-view Photometric Stereo (PS-GS), which efficiently and jointly estimates the geometry, materials, and lighting of the object that is illuminated by diverse directional lights (multi-light). Our method first reconstructs a standard 2D Gaussian splatting model as the initial geometry. Based on the initialization model, it then proceeds with the deferred inverse rendering by the full rendering equation containing a lighting-computing multi-layer perceptron. During the whole optimization, we regularize the rendered normal maps by the uncalibrated photometric stereo estimated normals. We also propose the 2D Gaussian ray-tracing for single directional light to refine the incident lighting. The regularizations and the use of multi-view and multi-light images mitigate the ill-posed problem of inverse rendering. After optimization, the reconstructed object can be used for novel-view synthesis, relighting, and material and shape editing. Experiments on both synthetic and real datasets demonstrate that our method outperforms prior works in terms of reconstruction accuracy and computational efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18231
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PS-GS: Gaussian Splatting for Multi-View Photometric Stereo
Chen, Yixiao
Liang, Bin
Guo, Hanzhi
Cheng, Yongqing
Zhao, Jiayi
Weng, Dongdong
Graphics
Computer Vision and Pattern Recognition
Integrating inverse rendering with multi-view photometric stereo (MVPS) yields more accurate 3D reconstructions than the inverse rendering approaches that rely on fixed environment illumination. However, efficient inverse rendering with MVPS remains challenging. To fill this gap, we introduce the Gaussian Splatting for Multi-view Photometric Stereo (PS-GS), which efficiently and jointly estimates the geometry, materials, and lighting of the object that is illuminated by diverse directional lights (multi-light). Our method first reconstructs a standard 2D Gaussian splatting model as the initial geometry. Based on the initialization model, it then proceeds with the deferred inverse rendering by the full rendering equation containing a lighting-computing multi-layer perceptron. During the whole optimization, we regularize the rendered normal maps by the uncalibrated photometric stereo estimated normals. We also propose the 2D Gaussian ray-tracing for single directional light to refine the incident lighting. The regularizations and the use of multi-view and multi-light images mitigate the ill-posed problem of inverse rendering. After optimization, the reconstructed object can be used for novel-view synthesis, relighting, and material and shape editing. Experiments on both synthetic and real datasets demonstrate that our method outperforms prior works in terms of reconstruction accuracy and computational efficiency.
title PS-GS: Gaussian Splatting for Multi-View Photometric Stereo
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.18231