Research map / 3D vision / NeRF and radiance fields
Neural Microfacet Fields for Inverse Rendering
Alexander Mai, Dor Verbin, Falko Kuester, Sara Fridovich-Keil
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 integral images (mean over solid-angle rectangle) for far-field environment map queries (ablation) | Neural Microfacet Fields · Shiny Blender (view synthesis) | PSNR: 27.33 -> 34.56 | Improved |
| use smoothed numerical derivative of density instead of analytical gradient for normals (ablation) | Neural Microfacet Fields · Shiny Blender (normals) | MAE (degrees): 7.43 -> 2.78 | Improved |
| add multi-bounce interreflections (ablation) | Neural Microfacet Fields · Blender (view synthesis) | PSNR: 30.68 -> 30.71 | Improved |
| add multi-bounce interreflections (ablation) | Neural Microfacet Fields · Shiny Blender (view synthesis) | PSNR: 34.39 -> 34.56 | Improved |
| add neural network g to the BRDF instead of identity (ablation) | Neural Microfacet Fields · Shiny Blender (view synthesis) | PSNR: 33.00 -> 34.56 | Improved |
| use Neural Microfacet Fields instead of NVDiffRecMC for relighting | Shiny Blender relighting · Shiny Blender relighting (mean) | PSNR: 20.70 -> 25.17 | Improved |
| use Neural Microfacet Fields vs Ref-NeRF (a view synthesis method) for novel view synthesis | Neural Microfacet Fields · Blender (view synthesis) | PSNR: 33.99 -> 30.71 | Hurt |
| use Neural Microfacet Fields instead of Ref-NeRF for normals | Neural Microfacet Fields · Shiny Blender (normals) | MAE (degrees): 18.38 -> 2.78 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- Ref-NeRF — Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields (CVPR 2022) · better on 1 of 3 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
- Inverse Image-Based Rendering for Light Field Generation from Single Images (ICCV 2025 · similarity 0.91)
- Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields (CVPR 2024 · similarity 0.90)
- Multi-times Monte Carlo Rendering for Inter-reflection Reconstruction (NeurIPS 2024 · similarity 0.90)
- Neural Inverse Rendering from Propagating Light (CVPR 2025 · similarity 0.89)
- Differentiable Neural Surface Refinement for Modeling Transparent Objects (CVPR 2024 · similarity 0.89)
- VMINer: Versatile Multi-view Inverse Rendering with Near- and Far-field Light Sources (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.
