Research map / 3D vision / Face and shape
ReDA:Reinforced Differentiable Attribute for 3D Face Reconstruction
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 |
|---|---|---|---|
| Add mask attributes alongside color attributes (ablation) | ReDA face fitting · MICC | point-to-plane fitting error: 5.1% | Helped |
| Add mask attributes alongside color attributes (ablation) | ReDA face fitting · BU-3DFE | point-to-plane fitting error: 13.9% | Helped |
| Add depth attributes to color and mask (ablation) | ReDA face fitting · BU-3DFE | point-to-plane fitting error: 52.5% | Helped |
| Replace Z-buffer rasterization with ReDA rasterization (ablation) | ReDA face fitting · MICC, color attribute | point-to-plane fitting error: 14.3% | Helped |
| Replace Z-buffer rasterization with ReDA rasterization (ablation) | ReDA face fitting · MICC, mask attribute | point-to-plane fitting error: 26.6% | Helped |
| Replace Z-buffer rasterization with ReDA rasterization (ablation) | ReDA face fitting · MICC, color + mask | point-to-plane fitting error: 23.3% | Helped |
| Add free-form deformation with ARAP constraint (ablation) | ReDA face fitting · BU-3DFE | point-to-plane fitting error: 11.7% | Helped |
| Use ReDA rasterization pyramid level 6 (ablation) | ReDA rasterization with color + mask · BU-3DFE | point-to-plane fitting error: 1.331 | Helped |
Closest papers by meaning
- Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction (ICLR 2026 · similarity 0.87)
- Generating Diverse 3D Reconstructions From a Single Occluded Face Image (CVPR 2022 · similarity 0.87)
- Extreme 3D Face Reconstruction: Seeing Through Occlusions (CVPR 2018 · similarity 0.86)
- Adaptive 3D Face Reconstruction From Unconstrained Photo Collections (CVPR 2016 · similarity 0.86)
- Deep Facial Non-Rigid Multi-View Stereo (CVPR 2020 · similarity 0.86)
- OFER: Occluded Face Expression Reconstruction (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.