Research map / 3D vision / NeRF and radiance fields
NeMF: Inverse Volume Rendering with Neural Microflake Field
Youjia Zhang, Teng Xu, Junqing Yu, Yuteng Ye, Yanqing Jing, Junle Wang, Jingyi Yu, Wei Yang
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 density and microflake normal regularization (ablation) | NeMF · Synthetic scenes, relighting | PSNR: 18.6333 -> 25.7048 | Improved |
| add visibility modeling of direct illumination (ablation) | NeMF · Synthetic scenes, relighting | PSNR: 20.5587 -> 25.7048 | Improved |
| add latent space with sparsity constraint for albedo and roughness (ablation) | NeMF · Synthetic scenes, roughness | MSE: 0.0160 -> 0.0074 | Improved |
| add smoothness regularization on normals and latent (ablation) | NeMF · Synthetic scenes, relighting | PSNR: 24.9586 -> 25.7048 | Improved |
| add smoothness regularization on normals and latent (ablation) | NeMF · Synthetic scenes, roughness and albedo | roughness MSE; albedo PSNR: roughness MSE 0.0075 -> 0.0074; albedo PSNR 23.5721 -> 23.6982 | No clear effect |
| use more samples (ablation) | NeMF · Synthetic scenes, relighting | PSNR: 22.2603 -> 25.7048 | Improved |
| remove visibility modeling effect on view synthesis (ablation) | NeMF · Synthetic scenes, view synthesis | PSNR: 28.6739 -> 28.8920 | No clear effect |
| replace InvRender with NeMF volumetric microflake representation | InvRender · Synthetic scenes, relighting | PSNR: 24.5309 -> 25.7048 | Improved |
| NeMF versus InvRender on albedo perceptual quality | NeMF · Synthetic scenes, albedo | LPIPS: 0.0811 -> 0.0870 | Hurt |
Closest papers by meaning
- Neural Microfacet Fields for Inverse Rendering (ICCV 2023 · similarity 0.90)
- NeuTex: Neural Texture Mapping for Volumetric Neural Rendering (CVPR 2021 · similarity 0.88)
- NeISF: Neural Incident Stokes Field for Geometry and Material Estimation (CVPR 2024 · similarity 0.86)
- LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fields (CVPR 2025 · similarity 0.86)
- ProbeSDF: Light Field Probes For Neural Surface Reconstruction (CVPR 2025 · similarity 0.85)
- PBR-NeRF: Inverse Rendering with Physics-Based Neural Fields (CVPR 2025 · similarity 0.85)
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.
