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

2026-03-11

AI Summary

This work addresses the limitations of existing 3D Gaussian splatting methods in accurately reconstructing fine geometry and surface normals of specular objects, where they underperform compared to implicit neural approaches. The paper introduces, for the first time, physics-guided polarization cues into the Gaussian splatting framework. By leveraging a polarized BRDF model, it explicitly decouples diffuse and specular reflectance components. Furthermore, it proposes a depth-guided visibility mask and an angle-of-polarization (AoP)-based tangent-space consistency constraint, enabling efficient modeling of reflective properties without ray tracing. Evaluated on both synthetic and real-world datasets, the method significantly improves geometric and normal reconstruction accuracy for reflective surfaces, achieving high-quality results in approximately 10 minutes of training.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Feature Construction/Reformulation
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Security and Privacy: Data transparency and provenance
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• reflective surface reconstruction
• 3D Gaussian Splatting
• polarimetric imaging
• surface normals
• computer vision

Innovation

• Polarimetric Gaussian Splatting
• pBRDF
• Reflective Surface Reconstruction
• Angle of Polarization
• Physically-Guided Rendering