Research map / Image generation / Image restoration
Bridging Information Asymmetry: A Hierarchical Framework for Deterministic Blind Face Restoration
Zhengjian Yao, Jiakui Hu, Kaiwen Li, Hangzhou He, Xinliang Zhang, Shuang Zeng, Lei Zhu, Yanye Lu
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 Stage 2 fidelity-constrained preference optimization (ablation) | Pref-Restore · CelebA-Test (synthetic) | LPIPS: 0.3916 -> 0.3657 | Improved |
| add Stage 2 fidelity-constrained preference optimization (ablation) | Pref-Restore · CelebA-Test (synthetic) | FID(HQ): 13.9015 -> 23.7305 | Hurt |
| add Stage 2 fidelity-constrained preference optimization (ablation) | Pref-Restore · CelebA-Test (synthetic) | ArcFace Deg: 54.9791 -> 51.5394 | Improved |
| add Stage 1.2 texture-to-diffusion alignment after Stage 1.1 (ablation) | Pref-Restore · CelebA-Test, staged alignment ablation | ArcFace Deg: 74.5286 -> 60.9876 | Improved |
| add Stage 1.2 texture-to-diffusion alignment after Stage 1.1 (ablation) | Pref-Restore · CelebA-Test, staged alignment ablation | LPIPS: 0.5272 -> 0.4413 | Improved |
| train semantic and texture alignment sequentially instead of jointly (ablation) | Pref-Restore · CelebA-Test, staged alignment ablation | ArcFace Deg: 62.1582 -> 60.9876 | Improved |
| use aesthetic-only reward in Stage 2 (ablation) | Pref-Restore · CelebA-Test, Stage 2 reward ablation | ArcFace Deg: 54.0623 -> 73.9882 | Hurt |
| add identity reward to aesthetic reward (ablation) | Pref-Restore · CelebA-Test, Stage 2 reward ablation | ArcFace Deg: 73.9882 -> 47.1055 | Improved |
| add geometry reward to identity + LPIPS rewards (ablation) | Pref-Restore · CelebA-Test, Stage 2 reward ablation | ArcFace Deg: 47.0899 -> 49.6654 | Hurt |
| add AR semantic branch without text (ablation) | Pref-Restore · CelebA-Test, text guidance | ArcFace Deg: 63.0939 -> 60.5767 | Improved |
| provide ground-truth captions at inference (ablation) | Pref-Restore (Train-Caption) · CelebA-Test, text guidance | ArcFace Deg: 60.9876 -> 54.3705 | Improved |
| provide captions generated from degraded input at inference (ablation) | Pref-Restore (Train-Caption) · CelebA-Test, text guidance | ArcFace Deg: 60.9876 -> 58.6068 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- DifFace — DifFace: Blind Face Restoration With Diffused Error Contraction (TPAMI 2024) · better on 1 of 1 shared result
- VQFR — VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder (ECCV 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- $InterLCM$: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration (ICLR 2025 · similarity 0.91)
- FaceMe: Robust Blind Face Restoration with Personal Identification (AAAI 2025 · similarity 0.89)
- Blind Face Restoration under Extreme Conditions: Leveraging 3D-2D Prior Fusion for Superior Structural and Texture Recovery (AAAI 2024 · similarity 0.89)
- Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model (ICLR 2025 · similarity 0.88)
- ReF-LDM: A Latent Diffusion Model for Reference-based Face Image Restoration (NeurIPS 2024 · similarity 0.88)
- Learning Degradation-unaware Representation with Prior-based Latent Transformations for Blind Face Restoration (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.
