Research map / 3D vision / Face and shape
Face De-Occlusion Using 3D Morphable Model and Generative Adversarial Network
Xiaowei Yuan, In Kyu Park
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 3DMM synthesis as generator input (ablation) | 3DMM-conditioned GAN · Face de-occlusion (qualitative) | visual quality | Improved |
| add global discriminator to generator-only model (ablation) | 3DMM-conditioned GAN · Face de-occlusion (qualitative) | visual quality | Improved |
| add local face-region discriminator to global discriminator (ablation) | 3DMM-conditioned GAN · Face de-occlusion (qualitative) | visual quality | Improved |
| increase occluded area from upper face to three quarters of face | 3DMM-conditioned GAN · Synthetic occlusion test set | PSNR: 34.0024 -> 22.1680 | Hurt |
| occlude lower face instead of upper face | 3DMM-conditioned GAN · Synthetic occlusion test set | SSIM: 0.9860 -> 0.9615 | Hurt |
| use de-occluded image instead of occluded image for shape-from-shading 3D reconstruction | 3D face reconstruction · Detailed 3D face reconstruction (qualitative) | geometry quality | Improved |
Closest papers by meaning
- Towards High-Fidelity Face Self-Occlusion Recovery via Multi-View Residual-Based GAN Inversion (AAAI 2022 · similarity 0.91)
- Uncertainty-Aware Mesh Decoder for High Fidelity 3D Face Reconstruction (CVPR 2020 · similarity 0.89)
- Regressing Robust and Discriminative 3D Morphable Models With a Very Deep Neural Network (CVPR 2017 · similarity 0.88)
- GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction (CVPR 2019 · similarity 0.88)
- Nonlinear 3D Face Morphable Model (CVPR 2018 · similarity 0.88)
- MVF-Net: Multi-View 3D Face Morphable Model Regression (CVPR 2019 · 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.
