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

TL;DR

PolGS++ introduces a physically-guided polarimetric Gaussian Splatting framework that significantly improves the speed and accuracy of reflective surface reconstruction by integrating a polarized BRDF model and a novel visibility mechanism.

Contribution

It presents a novel physically-guided approach combining pBRDF and AoP-based constraints within 3D Gaussian Splatting for fast, high-quality reflective surface reconstruction.

Findings

Achieves high-quality reconstruction in about 10 minutes of training.

Outperforms existing methods on synthetic and real datasets.

Effectively decouples diffuse and specular components for better geometry recovery.

Abstract

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.