PolarGS: Polarimetric Cues for Ambiguity-Free Gaussian Splatting with Accurate Geometry Recovery

Bo Guo1, Sijia Wen1 † , Yifan Zhao2, Jia Li2, Zhiming Zheng1,
1Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing,
School of Artificial Intelligence, Beihang University 2State Key Laboratory of Virtual Reality Technology and Systems, SCSE&QRI, Beihang University
(†Corresponding author)
Paper
teaser

Example results of our PolarGS. Our method not only produces faithful geometry in photometrically ambiguous regions, but can also serve as a plug-and-play module to improve 3DGS-based surface reconstruction pipelines.

Abstract

Recent advances in surface reconstruction for 3D Gaussian Splatting (3DGS) have enabled remarkable geometric accuracy. However, their performance degrades in photometrically ambiguous regions such as reflective and textureless surfaces, where unreliable cues disrupt photometric consistency and hinder accurate geometry estimation. Reflected light is often partially polarized in a manner that reveals surface orientation, making polarization an optic complement to photometric cues in resolving such ambiguities.

Therefore, we propose PolarGS, an optics-aware extension of RGB-based 3DGS that leverages polarization as an optical prior to resolve photometric ambiguities and enhance reconstruction accuracy. Specifically, we introduce two complementary modules: a polarization-guided photometric correction strategy, which ensures photometric consistency by identifying reflective regions via the Degree of Linear Polarization (DoLP) and refining reflective Gaussians with Color Refinement Maps; and a polarization-enhanced Gaussian densification mechanism for textureless area geometry recovery, which integrates both Angle and Degree of Linear Polarization (A/DoLP) into a PatchMatch-based depth completion process. This enables the back-projection and fusion of new Gaussians, leading to more complete reconstruction.

PolarGS is framework-agnostic and achieves superior geometric accuracy compared to state-of-theart methods.

Method

Pipeline
Overview of PolarGS. First, we preprocess polarized images to extract the s0 vector to initialize a Gaussian point cloud and compute the Polarimetric Reference Intensity (PRI). Based on PRI, we generate Color Refinement Maps (CRMs, i.e. Idiff and Ichro). During polar-guided photometric correction stage, we localize reflective regions and optimize reflective Gaussians using reflective-aware loss function supervised by CRMs. During polar-enhanced Gaussian densification stage, we integrate A/DoLP cues into the PatchMatch algorithm to predict depth maps, which are then back-projected into 3D space to generate new Gaussians. Finally, we apply TSDF fusion to rendered depth maps by α-blending for mesh extraction. It should be noted that PolarGS is compatible with various mesh extraction strategies and can be integrated into existing pipelines

Visual Results

Re-rendered View 1 Re-rendered View 2

Related Links

There's a lot of excellent work that was introduced about shape-from-polarization.

GNeRP extends NeRF-based surface learning to reflective scenes by introducing a Gaussian-based normal representation in SDF fields, supervised with polarization priors.

NeRSP targets reflective surface reconstruction under sparse views.

PISR improves orthographic projection via a perspective polarimetric constraint.

NeISF and NeISF++ first introduced neural rendering work that supports pBRDF decomposition modeling multi-bounce polarized light paths, and supports multiple materials, such as opaque, dielectric, dielectrics and conductors.