Research map / 3D vision / NeRF and radiance fields
NeFII: Inverse Rendering for Reflectance Decomposition With Near-Field Indirect Illumination
Haoqian Wu, Zhipeng Hu, Lincheng Li, Yongqiang Zhang, Changjie Fan, Xin Yu
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 |
|---|---|---|---|
| Use NeFII's joint path-tracing framework with cached neural indirect radiance | NeFII · Synthetic data | View synthesis specular RGB PSNR: 34.2930 vs 26.1370 | Improved |
| Use NeFII's joint path-tracing framework with cached neural indirect radiance | NeFII · Synthetic data | Roughness MSE: 0.0065 vs 0.0464 | Improved |
| Use NeFII's joint path-tracing framework with cached neural indirect radiance | NeFII · Synthetic data | View synthesis RGB SSIM: 0.9586 vs 0.9642 | Hurt |
| Represent environment illumination with SG coefficients and SG importance sampling instead of 2D environment maps and piece-constant sampling (ablation) | NeFII · Synthetic data | Diffuse albedo decomposition | Improved |
| Train with unobserved traced rays using radiance consistency (ablation) | NeFII · Synthetic data | Indirect illumination decomposition | Improved |
| Train with unobserved traced rays using radiance consistency (ablation) | NeFII · Synthetic data | Roughness at object interstices | Improved |
| Model indirect illumination and visibility rather than omit them (ablation) | NeFII · Synthetic data | Diffuse albedo decomposition | Improved |
| Model visibility along with indirect illumination (ablation) | NeFII · Synthetic data | Roughness estimation | Improved |
Later papers that compared with this method
1 later accepted paper reports Nefii as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Multi-times Monte Carlo Rendering for Inter-reflection Reconstruction (NeurIPS 2024 · better on 1 of 1 shared result)
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 Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields (CVPR 2024 · similarity 0.91)
- Inverse Rendering using Multi-Bounce Path Tracing and Reservoir Sampling (ICLR 2025 · similarity 0.90)
- Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects (CVPR 2025 · similarity 0.90)
- GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering (ICLR 2025 · similarity 0.90)
- RobIR: Robust Inverse Rendering for High-Illumination Scenes (NeurIPS 2024 · similarity 0.90)
- MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference (NeurIPS 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.
