PolarGuide-GSDR: 3D Gaussian Splatting Driven by Polarization Priors and Deferred Reflection for Real-World Reflective Scenes
This work solves the challenge of accurately modeling complex reflective scenes for applications in computer vision and graphics, representing an incremental improvement by integrating polarization priors into 3D Gaussian Splatting.
The paper tackles the problem of reconstructing reflective scenes in 3D by addressing limitations in existing methods like slow training and inaccurate reflections, achieving state-of-the-art performance in specular reconstruction, normal estimation, and novel view synthesis while maintaining real-time rendering.
Polarization-aware Neural Radiance Fields (NeRF) enable novel view synthesis of specular-reflection scenes but face challenges in slow training, inefficient rendering, and strong dependencies on material/viewpoint assumptions. However, 3D Gaussian Splatting (3DGS) enables real-time rendering yet struggles with accurate reflection reconstruction from reflection-geometry entanglement, adding a deferred reflection module introduces environment map dependence. We address these limitations by proposing PolarGuide-GSDR, a polarization-forward-guided paradigm establishing a bidirectional coupling mechanism between polarization and 3DGS: first 3DGS's geometric priors are leveraged to resolve polarization ambiguity, and then the refined polarization information cues are used to guide 3DGS's normal and spherical harmonic representation. This process achieves high-fidelity reflection separation and full-scene reconstruction without requiring environment maps or restrictive material assumptions. We demonstrate on public and self-collected datasets that PolarGuide-GSDR achieves state-of-the-art performance in specular reconstruction, normal estimation, and novel view synthesis, all while maintaining real-time rendering capabilities. To our knowledge, this is the first framework embedding polarization priors directly into 3DGS optimization, yielding superior interpretability and real-time performance for modeling complex reflective scenes.