Research map / 3D vision / NeRF and radiance fields
Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use Neural-PIL instead of MC integration | Illumination estimation · 6 rendered spheres, roughness 0.2 and 0.5 | PSNR: 34.88 -> 35.76; 35.14 -> 35.28 | Helped |
| Use Neural-PIL instead of spherical Gaussians | Illumination estimation · 6 rendered spheres, roughness 0.2 and 0.5 | PSNR: 31.57 -> 35.76; 28.98 -> 35.28 | Helped |
| Use the proposed decomposition method rather than NeRD | BRDF decomposition · Globe, Car, Chair | Diffuse PSNR: 18.24 -> 20.22 | Helped |
| Use the proposed decomposition method rather than NeRD | BRDF decomposition · Globe, Car, Chair | Specular PSNR: 25.70 -> 16.84 | Hurt |
| Use the proposed decomposition method rather than NeRD | BRDF decomposition · Globe, Car, Chair | Roughness PSNR: 15.00 -> 24.82 | Helped |
| Use the proposed method rather than NeRF | View synthesis · Synthetic | PSNR: 34.24 -> 30.08 | Hurt |
| Use the proposed method rather than NeRD | View synthesis and relighting · Synthetic | PSNR: 27.96 -> 29.24 | Helped |
| Use the proposed method rather than NeRD | View synthesis and relighting · Real-world | PSNR: 25.81 -> 26.23 | Helped |
| Add BRDF-SMAE to constrain the BRDF parameter space (ablation) | Neural-PIL decomposition method · 3 synthetic scenes under varying illumination | Diffuse PSNR: 11.87 -> 20.22 | Helped |
| Add BRDF-SMAE to constrain the BRDF parameter space (ablation) | Neural-PIL decomposition method · 3 synthetic scenes under varying illumination | Specular PSNR: 9.24 -> 16.84 | Helped |
| Add BRDF-SMAE to constrain the BRDF parameter space (ablation) | Neural-PIL decomposition method · 3 synthetic scenes under varying illumination | Roughness PSNR: 16.51 -> 24.82 | Helped |
Closest papers by meaning
- DeRF: Decomposed Radiance Fields (CVPR 2021 · similarity 0.89)
- A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields (AAAI 2024 · similarity 0.88)
- Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields (CVPR 2022 · similarity 0.87)
- Bright-NeRF: Brightening Neural Radiance Field with Color Restoration from Low-Light RAW Images (AAAI 2025 · similarity 0.87)
- Few-Shot Neural Radiance Fields under Unconstrained Illumination (AAAI 2024 · similarity 0.86)
- SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild (CVPR 2024 · similarity 0.86)
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.