Research map / Image generation / Super-resolution
Fair and Faithful: A Diffusion-Enhanced Dataset and Hybrid State-Space Mamba for Face Super-Resolution
Tao Wang, Peiwen Xia, Bowen Tang, Jinwei Chen, Kaihao Zhang, Bo Li
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 region-adaptive scan to global scan (ablation) | GLASNet · SFHQFSR scan ablation | PSNR: 30.13 -> 30.73 | Improved |
| use region-adaptive scan alone instead of global scan (ablation) | GLASNet · SFHQFSR scan ablation | PSNR: 30.13 -> 30.41 | Improved |
| apply global scan first then region-adaptive scan (instead of reverse) (ablation) | GLASNet · SFHQFSR scan ablation | PSNR: 30.73 -> 30.86 | Improved |
| add channel attention to refiner (ablation) | GLASNet refiner · SFHQFSR refiner ablation | PSNR: 28.30 -> 29.92 | Improved |
| add spatial attention to refiner (ablation) | GLASNet refiner · SFHQFSR refiner ablation | SSIM: 0.8312 -> 0.8214 | Mixed |
| add frequency attention to refiner (ablation) | GLASNet refiner · SFHQFSR refiner ablation | PSNR: 30.20 -> 30.86 | Improved |
| add frequency attention to refiner (ablation) | GLASNet refiner · SFHQFSR refiner ablation | SSIM: 0.8214 -> 0.8451 | Improved |
| increase HSSMG groups from 6 to 8 (ablation) | GLASNet · SFHQFSR | PSNR: 30.86 -> 30.90 | No clear effect |
| increase HSSMG groups from 2 to 6 (ablation) | GLASNet · SFHQFSR | PSNR: 30.18 -> 30.86 | Improved |
| train SFMNet on SFHQFSR instead of FFHQ | SFMNet · Helen BI x8 | PSNR: 24.02 -> 24.34 | Improved |
| train SFMNet on SFHQFSR instead of FFHQ | SFMNet · CelebA-test BI x8 | PSNR: 28.90 -> 29.28 | Improved |
| train SPARNet on SFHQFSR instead of FFHQ | SPARNet · CelebA-test BI x8 | PSNR: 29.09 -> 29.11 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FaceMe — FaceMe: Robust Blind Face Restoration with Personal Identification (AAAI 2025) · better on 2 of 2 shared results
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
- FSRNet: End-to-End Learning Face Super-Resolution With Facial Priors (CVPR 2018 · similarity 0.89)
- Face Super-resolution Guided by Facial Component Heatmaps (ECCV 2018 · similarity 0.89)
- Extreme Face Super-Resolution through Identity Fitting and Decoupling (ECCV 2026 · similarity 0.88)
- Face Super-Resolution Guided by 3D Facial Priors (ECCV 2020 · similarity 0.88)
- Low-Light Face Super-resolution via Illumination, Structure, and Texture Associated Representation (AAAI 2024 · similarity 0.87)
- Diffusion Prior Interpolation for Flexibility Real-World Face Super-Resolution (AAAI 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.
