Research map / 3D vision / Face and shape
A Morphable Face Albedo Model
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 |
|---|---|---|---|
| Replace BFM 2017 texture with the proposed diffuse and specular albedo model | BFM 2017 inverse-rendering fitting pipeline · Albedo estimation (reconstruction) | mean squared error: 0.0192 ± 0.0121 -> 0.0060 ± 0.0022 | Helped |
| Replace BFM 2017 texture with the proposed diffuse and specular albedo model | BFM 2017 inverse-rendering fitting pipeline · Albedo estimation (model mean) | mean squared error: 0.0575 ± 0.0551 -> 0.0170 ± 0.0270 | Helped |
| Use diffuse-model principal-component weights for the specular model instead of an independent specular PCA (ablation) | Proposed diffuse/specular albedo model · Leave-one-out generalisation | generalisation error | Mixed |
| Use a concatenated joint diffuse/specular PCA instead of independent models (ablation) | Proposed diffuse/specular albedo model · Leave-one-out generalisation | generalisation error | Mixed |
| Iterate statistical inpainting and rebuild the model from completed textures (ablation) | Proposed albedo model · Albedo inpainting | model improvement | No clear effect |
| Use statistical inpainting alone instead of statistical inpainting followed by Poisson blending (ablation) | Proposed albedo-map completion pipeline · Albedo inpainting | seam artifacts | Hurt |
| Apply gamma during albedo reconstruction (ablation) | BFM albedo reconstruction · Albedo reconstruction with known ground truth | albedo reconstruction performance | Helped |
Closest papers by meaning
- Learning a 3D Morphable Face Reflectance Model From Low-Cost Data (CVPR 2023 · similarity 0.93)
- Improving Fairness in Facial Albedo Estimation via Visual-Textual Cues (CVPR 2023 · similarity 0.90)
- S^3-Face: SSS-Compliant Facial Reflectance Estimation via Diffusion Priors (CVPR 2025 · similarity 0.89)
- Monocular Identity-Conditioned Facial Reflectance Reconstruction (CVPR 2024 · similarity 0.87)
- SFDM: Robust Decomposition of Geometry and Reflectance for Realistic Face Rendering from Sparse-view Images (CVPR 2025 · similarity 0.86)
- Diffusion Reflectance Map: Single-Image Stochastic Inverse Rendering of Illumination and Reflectance (CVPR 2024 · 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.