Research map / 3D vision / NeRF and radiance fields
NeRD: Neural Reflectance Decomposition From Image Collections
Mark Boss, Raphael Braun, Varun Jampani, Jonathan T. Barron, Ce Liu, Hendrik P.A. Lensch
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 gradient-based normals (ablation) | NeRD · Globe ablation | MSE re-render: 0.0893 -> 0.0592 | Improved |
| add gradient-based normals (ablation) | NeRD · Globe ablation | MSE base color: 0.1264 -> 0.0796 | Improved |
| add gradient-based normals (ablation) | NeRD · Globe ablation | MSE metalness: 0.1203 -> 0.0784 | Improved |
| add compressed BRDF space (ablation) | NeRD · Globe ablation | MSE metalness: 0.2496 -> 0.0784 | Improved |
| add compressed BRDF space (ablation) | NeRD · Globe ablation | MSE re-render: 0.0759 -> 0.0592 | Improved |
| add white balancing (ablation) | NeRD · Globe ablation | MSE re-render: 0.0655 -> 0.0592 | Improved |
| add white balancing (ablation) | NeRD · Globe ablation | MSE base color: 0.1059 -> 0.0796 | Improved |
| joint shape and SVBRDF optimization instead of per-image BRDF (Li et al.) | NeRD · BRDF estimation diffuse | PSNR: 1.06 -> 18.24 | Improved |
| joint optimization instead of Li et al. | NeRD · BRDF estimation roughness | PSNR: 17.18 -> 15.00 | Hurt |
| add per-image appearance latent (NeRF-A) to NeRF | NeRF · Synthetic varying illumination | PSNR: 21.05 -> 28.53 | Improved |
| use NeRD decomposition instead of NeRF | NeRF · Synthetic varying illumination | PSNR: 21.05 -> 27.96 | Improved |
| use NeRD instead of NeRF | NeRF · Synthetic fixed illumination | PSNR: 34.24 -> 30.07 | Hurt |
Later papers that compared with this method
2 later accepted papers report NeRD as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation (CVPR 2025 · better on 4 of 4 shared results)
- Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition (NeurIPS 2021 · better on 7 of 9 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
- Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition (NeurIPS 2021 · similarity 0.91)
- DeRF: Decomposed Radiance Fields (CVPR 2021 · similarity 0.91)
- A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields (AAAI 2024 · similarity 0.89)
- Real-Time Neural BRDF with Spherically Distributed Primitives (CVPR 2024 · similarity 0.88)
- PBR-NeRF: Inverse Rendering with Physics-Based Neural Fields (CVPR 2025 · similarity 0.88)
- Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields (CVPR 2024 · similarity 0.88)
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.
