Research map / 3D vision / Gaussian splatting
PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction
Yufei Han, Bowen Tie, Heng Guo, Youwei Lyu, Si Li, Boxin Shi, Yunpeng Jia, Zhanyu Ma
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 polarimetric Stokes loss L_pol (ablation) | PolGS · SMVP3D + RMVP3D mean | mean angular error (deg): 14.89 -> 14.35 | Improved |
| add polarimetric Stokes loss L_pol (ablation) | PolGS · SMVP3D + RMVP3D mean | Chamfer distance (mm): 7.80 -> 7.57 | Improved |
| add L_pol on texture-less David statue (ablation) | PolGS · SMVP3D David | mean angular error (deg): 15.44 -> 13.99 | Improved |
| add L_pol on Dragon (ablation) | PolGS · SMVP3D Dragon | mean angular error (deg): 25.74 -> 24.23 | Improved |
| add L_pol on Snail (ablation) | PolGS · SMVP3D Snail | Chamfer distance (mm): 10.75 -> 10.85 | No clear effect |
| add L_pol for texture-rich surfaces with dense views (ablation) | PolGS · texture-rich objects, >30 views | reconstruction accuracy | No clear effect |
| add L_pol with fewer input views (ablation) | PolGS · PISR texture-less real data | reconstruction quality | Improved |
| PolGS instead of Gaussian Surfels | Gaussian Surfels · SMVP3D + RMVP3D mean | Chamfer distance (mm): 10.30 -> 7.57 | Improved |
| PolGS instead of 3DGS-DR | 3DGS-DR · SMVP3D + RMVP3D mean | mean angular error (deg): 19.76 -> 14.35 | Improved |
| PolGS (3DGS) instead of SDF-based NeRSP in training time | NeRSP · SMVP3D + RMVP3D | training time (hours): 10 h -> 0.1 h | Improved |
| SDF-based NeRO versus PolGS | PolGS · SMVP3D + RMVP3D mean | mean angular error (deg): 14.35 vs 8.27 for NeRO | Hurt |
Later papers that compared with this method
1 later accepted paper reports PolGS as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- PhyGaP: Physically-Grounded Gaussians with Polarization Cues (CVPR 2026 · better on 1 of 2 shared results)
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.
- NeRSP — NeRSP: Neural 3D Reconstruction for Reflective Objects with Sparse Polarized Images (CVPR 2024) · better on 1 of 3 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
- GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstruction (CVPR 2025 · similarity 0.91)
- Reflective Gaussian Splatting (ICLR 2025 · similarity 0.90)
- SpecTRe-GS: Modeling Highly Specular Surfaces with Reflected Nearby Objects by Tracing Rays in 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
- High-Fidelity Polarimetric Implicit 3D Reconstruction with View-Dependent Physical Representation (AAAI 2025 · similarity 0.90)
- MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference (NeurIPS 2025 · similarity 0.89)
- GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors (ICLR 2024 · 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.
