Research map / 3D vision / Gaussian splatting
Geometric-Photometric Event-based 3D Gaussian Ray Tracing
Kai Kohyama, Yoshimitsu Aoki, Guillermo Gallego, Shintaro Shiba
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 geometric contrast loss (ablation) | GPERT · EDS | PSNR: 15.520 -> 19.470 | Improved |
| add geometric contrast loss (ablation) | GPERT · Synthetic color | PSNR: 9.600 -> 23.110 | Improved |
| add geometric contrast loss (ablation) | GPERT · TUM-VIE | PSNR: 13.450 -> 13.090 | Mixed |
| add IWE-based initialization (ablation) | GPERT · EDS | PSNR: 17.340 -> 19.470 | Improved |
| add IWE-based initialization (ablation) | GPERT · TUM-VIE | PSNR: 11.360 -> 13.090 | Improved |
| add IWE-based initialization (ablation) | GPERT · Synthetic color | PSNR: 20.820 -> 23.110 | Improved |
| render intensity once with warped events vs render twice (ablation) | GPERT · TUM-VIE (1d-trans, desk2) | PSNR/SSIM vs number of events | Improved |
| use GPERT instead of EventSplat | GPERT · EDS | PSNR: 18.860 -> 19.470 | Improved |
| use GPERT instead of Robust E-NeRF on color synthetic data | GPERT · Synthetic color | PSNR: 28.190 -> 23.110 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- EventSplat — EventSplat: 3D Gaussian Splatting from Moving Event Cameras for Real-time Rendering (CVPR 2025) · better on 3 of 6 shared results
- IncEventGS — IncEventGS: Pose-Free Gaussian Splatting from a Single Event Camera (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
- Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.92)
- EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting (ICML 2024 · similarity 0.91)
- EventSplat: 3D Gaussian Splatting from Moving Event Cameras for Real-time Rendering (CVPR 2025 · similarity 0.90)
- GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation (NeurIPS 2025 · similarity 0.90)
- EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.90)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.87)
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.
