Research map / 3D vision / Face and shape
Blind Face Restoration via Integrating Face Shape and Generative Priors
Feida Zhu, Junwei Zhu, Wenqing Chu, Xinyi Zhang, Xiaozhong Ji, Chengjie Wang, Ying Tai
Check 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 a 3D-image encoder branch to provide shape-prior spatial features (ablation) | SGPN · Real-world face restoration | FID: 24.36 -> 22.94 | Improved |
| use adaptive feature fusion instead of directly adding encoded spatial features (ablation) | SGPN · Real-world face restoration | FID: 23.42 -> 22.94 | Improved |
| add mesh-level 3D landmark and mesh losses during training (ablation) | SGPN · Real-world face restoration | FID: 24.63 -> 22.94 | Improved |
Closest papers by meaning
- Towards Real-World Blind Face Restoration With Generative Facial Prior (CVPR 2021 · similarity 0.91)
- Blind Face Restoration under Extreme Conditions: Leveraging 3D-2D Prior Fusion for Superior Structural and Texture Recovery (AAAI 2024 · similarity 0.91)
- GAN Prior Embedded Network for Blind Face Restoration in the Wild (CVPR 2021 · similarity 0.89)
- FaceMe: Robust Blind Face Restoration with Personal Identification (AAAI 2025 · similarity 0.87)
- Learning Degradation-unaware Representation with Prior-based Latent Transformations for Blind Face Restoration (CVPR 2024 · similarity 0.87)
- OSDFace: One-Step Diffusion Model for Face Restoration (CVPR 2025 · similarity 0.86)
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.
