Research map / 3D vision / Gaussian splatting
P2GS: Physical Prior-guided Gaussian Splatting for Photometrically Consistent Urban Reconstruction
Kota Shimomura, Hidehisa Arai, Tsubasa Takahashi, Takayoshi Yamashita, Hironobu Fujiyoshi
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 relative exposure consistency loss L_exp (ablation) | P2GS · Waymo Open (ablation) | PSNR: 27.88 -> 33.61 | Improved |
| add regularization terms L_reg on exposure and gamma (ablation) | P2GS · Waymo Open (ablation) | PSNR: 27.47 -> 33.61 | Improved |
| add relative exposure consistency loss L_exp (ablation) | P2GS · Waymo Open (ablation) | LPIPS: 0.237 -> 0.214 | Improved |
| add regularization terms L_reg (ablation) | P2GS · Waymo Open (ablation) | SSIM: 0.920 -> 0.941 | Improved |
| apply Difix3D post-processing | 3DGS · Waymo Open (reconstruction) | PSNR: 33.62 -> 26.95 | Hurt |
| apply Difix3D post-processing | PVG · Waymo Open (reconstruction) | HIS: 0.365 -> 0.417 | Hurt |
| replace 3DGS with P2GS HDR-domain optimization | 3DGS · Waymo Open (reconstruction) | LPIPS: 0.230 -> 0.209 | Improved |
| replace 3DGS with P2GS | 3DGS · Waymo Open (reconstruction) | PSNR: 33.62 -> 31.02 | Hurt |
| replace 3DGS with P2GS | 3DGS · Waymo Open (NVS) | PSNR: 30.39 -> 28.34 | Hurt |
| add affine exposure transform | 3DGS · CARLA (reconstruction, ISO std4) | PSNR: 19.25 -> 19.11 | No clear effect |
| increase exposure noise from ISO std2 to std4 | 3DGS · CARLA (reconstruction) | Delta PSNR: -2.20 | Hurt |
| increase exposure noise from ISO std2 to std4 | P2GS · CARLA (NVS) | PSNR: 22.72 -> 21.77 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Luminance-GS — Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustment (CVPR 2025) · better on 2 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
- SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving (CVPR 2025 · similarity 0.90)
- EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis (CVPR 2025 · similarity 0.90)
- DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes (CVPR 2024 · similarity 0.90)
- CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes (ICLR 2025 · similarity 0.90)
- Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting (NeurIPS 2025 · similarity 0.89)
- SplatFormer: Point Transformer for Robust 3D Gaussian Splatting (ICLR 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.
