Research map / 3D vision / Face and shape
Learning Complete 3D Morphable Face Models From Images and Videos
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 |
|---|---|---|---|
| learn identity geometry, expression, and albedo models jointly from in-the-wild images and videos | Ours · BU-3DFE | geometric reconstruction error (mm), mean: 1.78 -> 1.75 | Helped |
| add segmentation consistency loss (ablation) | Ours · Lip regions | upper lip IoU: 0.49 -> 0.52 | Helped |
| add segmentation consistency loss (ablation) | Ours · Lip regions | lower lip IoU: 0.53 -> 0.61 | Helped |
| add disentanglement loss on neutral faces (ablation) | Ours · Neutral faces | average expression deformation (AE): 2.5075 -> 0.0116 | Helped |
| add perceptual loss (ablation) | Ours · In-the-wild face reconstruction | photorealism of albedo and final overlay | Helped |
| train with a three-stage curriculum: pose pretraining, identity pretraining, then combined training | Ours · Training | training stability and identity-expression disentanglement | Helped |
Closest papers by meaning
- Self-Supervised Multi-Level Face Model Learning for Monocular Reconstruction at Over 250 Hz (CVPR 2018 · similarity 0.94)
- Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction (ICLR 2026 · similarity 0.91)
- 3D Facial Expressions through Analysis-by-Neural-Synthesis (CVPR 2024 · similarity 0.90)
- Monocular Identity-Conditioned Facial Reflectance Reconstruction (CVPR 2024 · similarity 0.90)
- OFER: Occluded Face Expression Reconstruction (CVPR 2025 · similarity 0.89)
- Learning Person-Specific Animatable Face Models from In-the-Wild Images via a Shared Base Model (CVPR 2025 · similarity 0.88)
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.