PolGS++: Physically-Guided Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Han, Yufei, Zhou, Chu, Lyu, Youwei, Chen, Qi, Li, Si, Shi, Boxin, Jia, Yunpeng, Guo, Heng, Ma, Zhanyu
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911506234343424
author Han, Yufei
Zhou, Chu
Lyu, Youwei
Chen, Qi
Li, Si
Shi, Boxin
Jia, Yunpeng
Guo, Heng
Ma, Zhanyu
author_facet Han, Yufei
Zhou, Chu
Lyu, Youwei
Chen, Qi
Li, Si
Shi, Boxin
Jia, Yunpeng
Guo, Heng
Ma, Zhanyu
contents Accurate reconstruction of reflective surfaces remains a fundamental challenge in computer vision, with broad applications in real-time virtual reality and digital content creation. Although 3D Gaussian Splatting (3DGS) enables efficient novel-view rendering with explicit representations, its performance on reflective surfaces still lags behind implicit neural methods, especially in recovering fine geometry and surface normals. To address this gap, we propose PolGS++, a physically-guided polarimetric Gaussian Splatting framework for fast reflective surface reconstruction. Specifically, we integrate a polarized BRDF (pBRDF) model into 3DGS to explicitly decouple diffuse and specular components, providing physically grounded reflectance modeling and stronger geometric cues for reflective surface recovery. Furthermore, we introduce a depth-guided visibility mask acquisition mechanism that enables angle-of-polarization (AoP)-based tangent-space consistency constraints in Gaussian Splatting without costly ray-tracing intersections. This physically guided design improves reconstruction quality and efficiency, requiring only about 10 minutes of training. Extensive experiments on both synthetic and real-world datasets validate the effectiveness of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2603_10801
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PolGS++: Physically-Guided Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction
Han, Yufei
Zhou, Chu
Lyu, Youwei
Chen, Qi
Li, Si
Shi, Boxin
Jia, Yunpeng
Guo, Heng
Ma, Zhanyu
Computer Vision and Pattern Recognition
Accurate reconstruction of reflective surfaces remains a fundamental challenge in computer vision, with broad applications in real-time virtual reality and digital content creation. Although 3D Gaussian Splatting (3DGS) enables efficient novel-view rendering with explicit representations, its performance on reflective surfaces still lags behind implicit neural methods, especially in recovering fine geometry and surface normals. To address this gap, we propose PolGS++, a physically-guided polarimetric Gaussian Splatting framework for fast reflective surface reconstruction. Specifically, we integrate a polarized BRDF (pBRDF) model into 3DGS to explicitly decouple diffuse and specular components, providing physically grounded reflectance modeling and stronger geometric cues for reflective surface recovery. Furthermore, we introduce a depth-guided visibility mask acquisition mechanism that enables angle-of-polarization (AoP)-based tangent-space consistency constraints in Gaussian Splatting without costly ray-tracing intersections. This physically guided design improves reconstruction quality and efficiency, requiring only about 10 minutes of training. Extensive experiments on both synthetic and real-world datasets validate the effectiveness of our method.
title PolGS++: Physically-Guided Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.10801