Research map / 3D vision / Gaussian splatting
GHPT: Real-Time Relightable Gaussian Splatting using Hybrid Path Tracing
Jinyang Bo, Fan Dou, Wenrui Quan, Shangxun Liu, Yang Xu, Yuhe Zhang, Kang Li, Guohua Geng
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 GS-based FIPT stage on top of the underlying mesh rendering (ablation) | GHPT · Synthetic4Relight relighting | PSNR: 34.83 -> 35.87 | Improved |
| add spatial denoising (ablation) | GHPT · Synthetic4Relight relighting | LPIPS: 0.062 -> 0.045 | Improved |
| increase relighting samples from 16 to 256 spp (ablation) | GHPT · Synthetic4Relight relighting | PSNR: 34.87 -> 35.87 | Improved |
| increase relighting samples from 64 to 256 spp (ablation) | GHPT · Synthetic4Relight relighting | PSNR: 35.71 -> 35.87 | Improved |
| add indirect illumination in training and rendering (ablation) | GHPT · Synthetic4Relight relighting | PSNR: 34.68 -> 35.87 | Improved |
| add indirect illumination in training and rendering (ablation) | GHPT · TensoIR Synthetic relighting | PSNR: 32.28 -> 32.46 | Improved |
| add spatial denoising (ablation) | GHPT · TensoIR Synthetic relighting | PSNR: 32.06 -> 32.46 | Improved |
| hybrid path tracing on G-buffer vs approximate-formulation GS inverse rendering baselines | GHPT vs IRGS · Synthetic4Relight relighting | PSNR: 34.76 -> 35.87 | Improved |
| hybrid path tracing vs IRGS | GHPT · Synthetic4Relight albedo | PSNR: 33.07 -> 32.20 | Hurt |
| hybrid path tracing vs GI-GS | GHPT · TensoIR Synthetic novel view synthesis | PSNR: 36.75 -> 35.57 | Hurt |
| add path tracing (shadows, interreflections) to real-time composition (ablation) | GHPT · Mip-NeRF 360 composition | qualitative realism | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 3 on most shared results.
- IRGS — IRGS: Inter-Reflective Gaussian Splatting with 2D Gaussian Ray Tracing (CVPR 2025) · better on 3 of 4 shared results
- SVG-IR — SVG-IR: Spatially-Varying Gaussian Splatting for Inverse Rendering (CVPR 2025) · better on 1 of 2 shared results
- GI-GS — GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering (ICLR 2025) · better on 0 of 1 shared result
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
- Reflective Gaussian Splatting (ICLR 2025 · similarity 0.92)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.91)
- GaussianPro: 3D Gaussian Splatting with Progressive Propagation (ICML 2024 · similarity 0.91)
- GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering (ICLR 2025 · similarity 0.91)
- 3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting (CVPR 2025 · similarity 0.91)
- Subsurface Scattering for Gaussian Splatting (NeurIPS 2024 · similarity 0.91)
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.
