Research map / Image generation / Super-resolution
Residual Attribute Attention Network for Face Image Super-Resolution
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 |
|---|---|---|---|
| replace best prior method (FSRNet) with RAAN | face SR · CelebA x8 | PSNR: 26.82 -> 27.03 | Helped |
| replace SRResNet with RAAN | face SR · CelebA x8 | PSNR: 30.48 -> 31.22 | Helped |
| add attribute analysis network (attribute supervision) to dual-branch network (ablation) | RAAN · CelebA x8 | PSNR | Helped |
| attribute attention on texture branch vs shape branch (ablation) | RAAN · CelebA x8 | PSNR | Helped |
| use attribute attention on both shape and texture (ablation) | RAAN · CelebA x8 | PSNR | Helped |
| add original connection (ablation) | RAAN · CelebA x8 | PSNR | Helped |
| add interstage connection alone (ablation) | RAAN · CelebA x8 | PSNR | No clear effect |
| combine interstage and original connections (ablation) | RAAN · CelebA x8 | PSNR | Helped |
Closest papers by meaning
- FSRNet: End-to-End Learning Face Super-Resolution With Facial Priors (CVPR 2018 · similarity 0.89)
- Super-Resolving Very Low-Resolution Face Images With Supplementary Attributes (CVPR 2018 · similarity 0.88)
- Deep Face Super-Resolution With Iterative Collaboration Between Attentive Recovery and Landmark Estimation (CVPR 2020 · similarity 0.88)
- Facial Attribute Capsules for Noise Face Super Resolution (AAAI 2020 · similarity 0.88)
- Low-Light Face Super-resolution via Illumination, Structure, and Texture Associated Representation (AAAI 2024 · similarity 0.87)
- OSFFNet: Omni-Stage Feature Fusion Network for Lightweight Image Super-Resolution (AAAI 2024 · similarity 0.85)
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.