Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Yufei Han, Chu Zhou, Youwei Lyu, Qi Chen, Si Li, Boxin Shi, Yunpeng Jia, Heng Guo, Zhanyu Ma

TL;DR

PolGS++ is proposed, a physically-guided polarimetric Gaussian Splatting framework for fast reflective surface reconstruction that improves reconstruction quality and efficiency and introduces a depth-guided visibility mask acquisition mechanism that enables angle-of-polarization-based tangent-space consistency constraints in Gaussian Splatting without costly ray-tracing intersections.

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.

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

TL;DR

PolGS++ is proposed, a physically-guided polarimetric Gaussian Splatting framework for fast reflective surface reconstruction that improves reconstruction quality and efficiency and introduces a depth-guided visibility mask acquisition mechanism that enables angle-of-polarization-based tangent-space consistency constraints in Gaussian Splatting without costly ray-tracing intersections.

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.
Paper Structure (37 sections, 28 equations, 11 figures, 3 tables)

This paper contains 37 sections, 28 equations, 11 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. 3D reconstruction based on neural SDF representation
  4. 3D reconstruction based on 3DGS
  5. 3D reconstruction using polarized images
  6. Preliminaries
  7. Gaussian Surfels model
  8. Gaussian splatting
  9. Polarimetric image formation model
  10. Multi-view tangent space consistency with AoP
  11. Proposed method
  12. Analysis of surface normal representation
  13. SDF-based representation
  14. 3DGS-based representation
  15. Polarimetric information for reflective surfaces
  16. ...and 22 more sections

Figures (11)

  • Figure 1: Comparison of efficiency and accuracy on reflective surface reconstruction. Our method takes only 10 minutes while achieving a shape reconstruction accuracy (measured by Chamfer Distance in millimeters) comparable to that of the neural implicit surface representation-based method NeRO liu2023nero.
  • Figure 2: Comparison between SDF-based and 3DGS-based method on geometry representation. (Top) The surface normal of a point has a strong relationship with its opacity in NeuS wang2021neus. (Bottom) The surface normal of a point has no direct dependence on its opacity in Gaussian Surfels dai2024high.
  • Figure 3: Pipeline of PolGS++. We re-rendered Stokes vectors $\hat{s}$ by using the diffuse color $C$ from 3DGS and specular color $L_r$ from Cubemap encoder module, which is supervised by the ground truth Stokes information. Tangent-space consistency constrain is applied to the surface normal estimated by 3DGS with the depth-guided visibility mask and AoP information.
  • Figure 4: Comparison of visibility mask acquisition strategies between SDF-based methods and our method based on Gaussian Splatting.
  • Figure 5: Visualization of visibility masks of one current view in SDF-based networks and in PolGS++.
  • ...and 6 more figures