Research map / 3D vision / Face and shape
Regressing Robust and Discriminative 3D Morphable Models With a Very Deep Neural Network
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 |
|---|---|---|---|
| Regress 3DMM parameters with the proposed CNN instead of standard 3DMM fitting | 3D face reconstruction · MICC Florence Faces | 3DRMSE: 1.75$\pm$.42 -> 1.57$\pm$.33 | Helped |
| Pool predictions across frames (ablation) | Proposed 3DMM regressor · MICC Florence Faces | 3DRMSE: 1.57$\pm$.33 -> 1.53$\pm$.29 | Helped |
| Use both shape and texture parameters rather than shape alone (ablation) | Proposed 3DMM regressor · LFW | verification accuracy: 90.53$\pm$1.34 -> 92.35$\pm$1.29 | Helped |
| Use both shape and texture parameters rather than shape alone (ablation) | Proposed 3DMM regressor · YTF | verification accuracy: 88.28$\pm$1.84 -> 88.80$\pm$2.21 | Helped |
| Use both shape and texture parameters rather than shape alone (ablation) | Proposed 3DMM regressor · IJB-A | Rank-1: 72.3$\pm$1.4 -> 76.2$\pm$1.8 | Helped |
| Use texture parameters rather than 3D shape parameters (ablation) | Proposed 3DMM regressor · LFW | verification accuracy: 90.53$\pm$1.34 -> 90.6$\pm$1.07 | No clear effect |
| Use texture parameters rather than 3D shape parameters (ablation) | Proposed 3DMM regressor · YTF | verification accuracy: 88.28$\pm$1.84 -> 87.56$\pm$2.56 | No clear effect |
| Use texture parameters rather than 3D shape parameters (ablation) | Proposed 3DMM regressor · IJB-A | Rank-1: 72.3$\pm$1.4 -> 70.9$\pm$1.5 | No clear effect |
| Use a 101-layer ResNet rather than the 16-layer VGG-Face CNN (ablation) | 3DMM parameter regression · 3DMM regression | performance | Helped |
| Use asymmetric Euclidean loss with λ1=1 and λ2=3 rather than standard Euclidean loss (ablation) | 3DMM parameter regression · 3D face reconstruction | shape detail | Helped |
Closest papers by meaning
- MVF-Net: Multi-View 3D Face Morphable Model Regression (CVPR 2019 · similarity 0.92)
- Uncertainty-Aware Mesh Decoder for High Fidelity 3D Face Reconstruction (CVPR 2020 · similarity 0.91)
- Unsupervised Training for 3D Morphable Model Regression (CVPR 2018 · similarity 0.91)
- Nonlinear 3D Face Morphable Model (CVPR 2018 · similarity 0.91)
- Towards High-Fidelity Nonlinear 3D Face Morphable Model (CVPR 2019 · similarity 0.91)
- Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space (CVPR 2025 · similarity 0.89)
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.