Research map / 3D vision / Face and shape
Towards High-Fidelity Face Self-Occlusion Recovery via Multi-View Residual-Based GAN Inversion
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 |
|---|---|---|---|
| Use MvInvert instead of 3D face reconstruction baselines | Face self-occlusion recovery · CelebA | L1 distance: 0.052 -> 0.028; 0.034 -> 0.028 | Helped |
| Use MvInvert instead of 3D face reconstruction baselines | Face self-occlusion recovery · CelebA | PSNR: 26.58 -> 30.78; 29.69 -> 30.78 | Helped |
| Use MvInvert instead of 3D face reconstruction baselines | Face self-occlusion recovery · CelebA | SSIM: 0.826 -> 0.897; 0.894 -> 0.897 | Helped |
| Use MvInvert instead of 3D face reconstruction baselines | Face self-occlusion recovery · CelebA | evoLVe: 0.641 -> 0.878; 0.848 -> 0.878 | Helped |
| Use MvInvert instead of 3D face reconstruction baselines | Face self-occlusion recovery · CelebA | LightCNN: 0.724 -> 0.926; 0.900 -> 0.926 | Helped |
| Add the face discriminator (ablation) | MvInvert · Ablation study | PSNR: 28.10 -> 30.78 | Helped |
| Add the global texture discriminator (ablation) | MvInvert · Ablation study | PSNR: 27.83 -> 30.78 | Helped |
| Add the central texture discriminator (ablation) | MvInvert · Ablation study | PSNR: 29.34 -> 30.78 | Helped |
| Add the face discriminator (ablation) | MvInvert · Ablation study | SSIM: 0.831 -> 0.897 | Helped |
| Add the global texture discriminator (ablation) | MvInvert · Ablation study | SSIM: 0.817 -> 0.897 | Helped |
| Add the central texture discriminator (ablation) | MvInvert · Ablation study | SSIM: 0.865 -> 0.897 | Helped |
Closest papers by meaning
- GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction (CVPR 2019 · similarity 0.91)
- Learning To Restore 3D Face From In-the-Wild Degraded Images (CVPR 2022 · similarity 0.89)
- Towards High-Fidelity 3D Face Reconstruction From In-the-Wild Images Using Graph Convolutional Networks (CVPR 2020 · similarity 0.89)
- In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing (CVPR 2024 · similarity 0.88)
- Dual Encoder GAN Inversion for High-Fidelity 3D Head Reconstruction from Single Images (NeurIPS 2024 · similarity 0.87)
- Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation (CVPR 2024 · similarity 0.87)
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.