Research map / 3D vision / Face and shape
Learning to Regress 3D Face Shape and Expression From an Image Without 3D Supervision
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 |
|---|---|---|---|
| train RingNet without paired 2D-to-3D supervision | RingNet · Feng et al. benchmark LQ | median error (mm): 1.79 -> 1.63 | Helped |
| train RingNet without paired 2D-to-3D supervision | RingNet · Feng et al. benchmark HQ | median error (mm): 1.60 -> 1.58 | Helped |
| train RingNet without paired 2D-to-3D supervision | RingNet · NoW face challenge | mean error (mm): 1.57 -> 1.55 | Helped |
| increase the ring size from R=3 to R=6 (ablation) | RingNet · Validation set | median error (mm): 1.25 -> 1.19 | Helped |
| increase the ring size from R=4 to R=6 (ablation) | RingNet · Validation set | median error (mm): 1.24 -> 1.19 | Helped |
| increase the ring size from R=5 to R=6 (ablation) | RingNet · Validation set | median error (mm): 1.20 -> 1.19 | Helped |
| increase the ring size from R=3 to R=6 (ablation) | RingNet · Validation set | mean error (mm): 1.68 -> 1.63 | Helped |
| increase the ring size from R=4 to R=6 (ablation) | RingNet · Validation set | mean error (mm): 1.67 -> 1.63 | No clear effect |
| increase the ring size from R=5 to R=6 (ablation) | RingNet · Validation set | mean error (mm): 1.63 -> 1.63 | No clear effect |
Closest papers by meaning
- Learning Complete 3D Morphable Face Models From Images and Videos (CVPR 2021 · similarity 0.89)
- Regressing Robust and Discriminative 3D Morphable Models With a Very Deep Neural Network (CVPR 2017 · similarity 0.88)
- Learning Person-Specific Animatable Face Models from In-the-Wild Images via a Shared Base Model (CVPR 2025 · similarity 0.88)
- 3D Facial Expressions through Analysis-by-Neural-Synthesis (CVPR 2024 · similarity 0.86)
- TEASER: Token Enhanced Spatial Modeling for Expressions Reconstruction (ICLR 2025 · 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.