Research map / 3D vision / Face and shape
Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognition
Read the paperCheck 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 |
|---|---|---|---|
| Jointly train reconstruction with identification loss (ablation) | Proposed encoder-decoder · MICC | RMSE: 2.23±0.48 -> 2.00±0.32 | Helped |
| Jointly train reconstruction with identification loss (ablation) | Proposed encoder-decoder · LFW | verification accuracy: 68.00±2.21 -> 94.43±1.47 | Helped |
| Jointly train reconstruction with identification loss (ablation) | Proposed encoder-decoder · YTF | verification accuracy: 69.19±1.91 -> 88.74±1.03 | Helped |
| Remove identity disentangling and identification loss (ablation) | Proposed encoder-decoder · MICC | RMSE: 2.00±0.32 -> 2.51±0.57 | Hurt |
| Use jointly learned shape features instead of 3DMM-CNN shape features | Face recognition using reconstructed shapes · LFW | verification accuracy: 90.53±1.34 -> 94.43±1.47 | Helped |
| Use jointly learned shape features instead of 3DMM-CNN shape features | Face recognition using reconstructed shapes · YTF | verification accuracy: 88.28±1.84 -> 88.74±1.03 | Helped |
| Fuse reconstructed shape features with texture features | SphereFace on YTF · YTF | verification accuracy: 94.78% to 95.18% | Helped |
| Use the proposed direct dense-shape reconstruction method instead of 3DSR | 3D face reconstruction · MICC | RMSE: 2.07 -> 2.00 | Helped |
Closest papers by meaning
- Nonlinear 3D Face Morphable Model (CVPR 2018 · similarity 0.91)
- Regressing Robust and Discriminative 3D Morphable Models With a Very Deep Neural Network (CVPR 2017 · similarity 0.90)
- MVF-Net: Multi-View 3D Face Morphable Model Regression (CVPR 2019 · similarity 0.90)
- Disentangled Representation Learning for 3D Face Shape (CVPR 2019 · similarity 0.90)
- Uncertainty-Aware Mesh Decoder for High Fidelity 3D Face Reconstruction (CVPR 2020 · similarity 0.90)
- End-To-End 3D Face Reconstruction With Deep Neural Networks (CVPR 2017 · 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.