Research map / 3D vision / NeRF and radiance fields
Neural Relightable Participating Media Rendering
Quan Zheng, Gurprit Singh, Hans-peter Seidel
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 |
|---|---|---|---|
| replace NeRV with the proposed SH-based method | NeRV · Cow, point illumination | PSNR: 25.20 -> 34.20 | Improved |
| replace Bi et al. with the proposed method | Bi et al. · Cloud, point illumination | PSNR: 20.92 -> 33.51 | Improved |
| replace NeRV with the proposed method | NeRV · Bunny4-VaryG, point illumination | ELPIPS: 0.419 -> 0.257 | Improved |
| train with env + point illumination instead of point only | Bi et al. · Buddha3 | PSNR: 29.47 -> 23.41 | Hurt |
| train with env + point illumination instead of point only | Ours · Buddha3 | PSNR: 33.77 -> 34.03 | No clear effect |
| use BRDF scattering function (Ours+BRDF) instead of HG phase function (ablation) | Ours · Dragon | PSNR: 28.50 -> 28.32 | Hurt |
| use BRDF scattering function instead of HG phase function (ablation) | Ours · Armadillo | PSNR: 26.60 -> 26.46 | Hurt |
| use BRDF scattering function instead of HG phase function (ablation) | Ours · Dragon | ELPIPS: 0.564 -> 0.692 | Hurt |
| use BRDF variant on participating media Bunny scene (ablation) | Ours · Bunny | qualitative | Hurt |
| remove spherical harmonics (ablation) | Ours · Buddha | image quality | Hurt |
| set maximum SH band to 5 versus 1, 3, 7, 9 (ablation) | Ours · Buddha | PSNR/ELPIPS and inference time | Mixed |
| move test point light farther from training range | Ours · Bunny | image quality | Hurt |
Closest papers by meaning
- Modeling Indirect Illumination for Inverse Rendering (CVPR 2022 · similarity 0.92)
- A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields (AAAI 2024 · similarity 0.90)
- Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields (CVPR 2024 · similarity 0.89)
- IllumiNeRF: 3D Relighting Without Inverse Rendering (NeurIPS 2024 · similarity 0.89)
- UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting (NeurIPS 2025 · similarity 0.89)
- Neural Inverse Rendering from Propagating Light (CVPR 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.
