Research map / 3D vision / Face and shape
Light Sampling Field and BRDF Representation for Physically-based Neural Rendering
Jing Yang, Hanyuan Xiao, Wenbin Teng, Yunxuan Cai, Yajie Zhao
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 the proposed neural PBR shader instead of the strongest listed baseline, NeLF | Facial rendering · Facial rendering, 800×800 | PSNR: 33.80 -> 36.69 | Improved |
| Use the proposed neural PBR shader instead of Neural-PIL | Facial rendering · Facial rendering, 800×800 | SSIM: 0.9153 -> 0.9250 | Improved |
| Use the proposed neural PBR shader instead of Neural-PIL | Facial rendering · Facial rendering, 800×800 | LPIPS (VGG): 0.1082 -> 0.0664 | Improved |
| Use the neural PBR shader instead of Maya | Facial rendering · Facial rendering, 5760×5760 | render time (seconds): 7848s -> 158s | Improved |
| Use importance light sampling instead of uniform spherical sampling (ablation) | Light Sampling Field shader · Direct illumination, qualitative evaluation | lighting fidelity | Improved |
| Add location-aware local SH illumination instead of global SH (ablation) | Light Sampling Field shader · Face rendering under indirect illumination | rendering quality | Improved |
| Add the subsurface-scattering material layer (ablation) | Light Sampling Field shader · Face rendering under indirect illumination | rendering quality | Improved |
| Use low-frequency normals from coarse geometry instead of high-frequency normal maps (ablation) | Neural PBR face shader · Pore-level face rendering | detail sharpness | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Neural-PIL — Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition (NeurIPS 2021) · better on 3 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
- A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields (AAAI 2024 · similarity 0.88)
- Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields (CVPR 2024 · similarity 0.87)
- Material Palette: Extraction of Materials from a Single Image (CVPR 2024 · similarity 0.87)
- Real-Time Neural BRDF with Spherically Distributed Primitives (CVPR 2024 · similarity 0.86)
- PBR-NeRF: Inverse Rendering with Physics-Based Neural Fields (CVPR 2025 · similarity 0.86)
- SplitNeRF: Split Sum Approximation Neural Field for Joint Geometry, Illumination, and Material Estimation (NeurIPS 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.
