Research map / 3D vision / Gaussian splatting
PhyGaP: Physically-Grounded Gaussians with Polarization Cues
Jiale Wu, Xiaoyang Bai, Zongqi He, Weiwei Xu, Yifan Peng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add GridMap (ablation) | PhyGaP · david relighting | PSNR: 17.81 -> 19.18 | Improved |
| add GridMap (ablation) | PhyGaP · david relighting | LPIPS: 0.0321 -> 0.0255 | Improved |
| add GridMap (ablation) | PhyGaP · david relighting | SSIM: 0.967 -> 0.973 | Improved |
| add PolarDR (polarization loss) (ablation) | PhyGaP without GridMap · david relighting | PSNR: 15.56 -> 17.81 | Improved |
| add PolarDR (polarization loss) (ablation) | PhyGaP without GridMap · Mitsuba envmap david | PSNR: 10.69 -> 13.00 | Improved |
| add PolarDR (polarization loss) (ablation) | PhyGaP without GridMap · Mitsuba envmap matpre. | PSNR: 9.78 -> 15.82 | Improved |
| add GridMap (ablation) | PhyGaP · Mitsuba envmap david | PSNR: 13.00 -> 12.39 | Hurt |
| add GridMap (ablation) | PhyGaP · Mitsuba envmap matpre. | PSNR: 15.82 -> 17.46 | Improved |
| add GridMap (ablation) | PhyGaP · Mitsuba envmap teapot | PSNR: 12.17 -> 11.50 | Hurt |
| use polarization cues instead of RGB-only (vs Ref-Gaussian) | Gaussian splatting · normal cosine distance dog | Cosine distance: 0.1565 -> 0.0910 | Improved |
| use polarization cues instead of RGB-only (vs Ref-Gaussian) | Gaussian splatting · NVS owl | PSNR: 22.39 -> 28.14 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- PolGS — PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction (ICCV 2025) · better on 1 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference (NeurIPS 2025 · similarity 0.91)
- Reflective Gaussian Splatting (ICLR 2025 · similarity 0.90)
- GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering (ICLR 2025 · similarity 0.89)
- GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstruction (CVPR 2025 · similarity 0.89)
- Textured Gaussians for Enhanced 3D Scene Appearance Modeling (CVPR 2025 · similarity 0.89)
- IBGS: Image-Based Gaussian Splatting (NeurIPS 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
