Research map / 3D vision / Face and shape
Monocular Reconstruction of Neural Face Reflectance Fields
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 full neural reflectance-field method instead of Smith et al. | Monocular face reconstruction · CelebA-HQ reconstruction | Si-MSE: 0.017 -> 0.004 | Helped |
| Use the full neural reflectance-field method instead of Smith et al. | Monocular face reconstruction · Reflectance transfer | Si-MSE: 0.018 -> 0.002 | Helped |
| Use the full neural reflectance-field method instead of the strongest baseline | Monocular face reconstruction · CelebA-HQ reconstruction | Face dis: 0.650 -> 0.550 | Helped |
| Use the full neural reflectance-field method instead of the strongest baseline | Monocular face reconstruction · Reflectance transfer | Face dis: 0.605 -> 0.482 | Helped |
| Add source and target surface normal maps to the reflectance network (ablation) | Neural reflectance-field method · Light-stage OLAT reconstruction, same pose | Si-MSE: 0.00113 -> 0.00070 | Helped |
| Add source and target surface normal maps to the reflectance network (ablation) | Neural reflectance-field method · Light-stage OLAT reconstruction, different pose | Si-MSE: 0.00126 -> 0.00084 | Helped |
| Learn identity and expression geometry instead of using only the mean face mesh (ablation) | Neural reflectance-field method · CelebA-HQ reconstruction | Si-MSE: 0.011 -> 0.004 | Helped |
| Learn identity and expression geometry instead of using only the mean face mesh (ablation) | Neural reflectance-field method · CelebA-HQ reconstruction | Face dis: 0.550 -> 0.550 | No clear effect |
Closest papers by meaning
- Monocular Identity-Conditioned Facial Reflectance Reconstruction (CVPR 2024 · similarity 0.90)
- Learning a 3D Morphable Face Reflectance Model From Low-Cost Data (CVPR 2023 · similarity 0.88)
- S$^3$-NeRF: Neural Reflectance Field from Shading and Shadow under a Single Viewpoint (NeurIPS 2022 · similarity 0.88)
- SFDM: Robust Decomposition of Geometry and Reflectance for Realistic Face Rendering from Sparse-view Images (CVPR 2025 · similarity 0.87)
- S^3-Face: SSS-Compliant Facial Reflectance Estimation via Diffusion Priors (CVPR 2025 · similarity 0.87)
- SpecNeRF: Gaussian Directional Encoding for Specular Reflections (CVPR 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.