Research map / Image generation / Super-resolution
Deep Face Super-Resolution With Iterative Collaboration Between Attentive Recovery and Landmark Estimation
Check 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 iterative collaboration between SR recovery and landmark estimation | DIC · CelebA | PSNR: 26.48 -> 27.37 | Helped |
| Use iterative collaboration between SR recovery and landmark estimation | DIC · Helen | SSIM: 0.7759 -> 0.7933 | Helped |
| Train with adversarial and perceptual losses | DIC · CelebA | PSNR: 27.37 -> 26.34 | Hurt |
| Train with adversarial and perceptual losses | DIC · Helen | NRMSE: 0.3674 -> 0.3336 | Helped |
| Add landmark guidance and the alignment branch (ablation) | DIC without landmarks · CelebA | PSNR: 26.31 -> 27.37 | Helped |
| Add landmark guidance and the alignment branch (ablation) | DIC without landmarks · CelebA | SSIM: 0.7526 -> 0.7962 | Helped |
| Replace concatenated landmark maps with attentive fusion (ablation) | DIC-CL · CelebA | PSNR: 26.93 -> 27.37 | Helped |
| Replace concatenated landmark maps with attentive fusion (ablation) | DIC-CL · CelebA | SSIM: 0.7811 -> 0.7962 | Helped |
| Increase recurrent collaboration from Step 1 to Step 4 (ablation) | DIC · CelebA | PSNR: 24.41 -> 26.34 | Helped |
| Increase recurrent collaboration from Step 1 to Step 4 (ablation) | DIC · Helen | NRMSE: 0.1057 -> 0.0520 | Helped |
Closest papers by meaning
- FSRNet: End-to-End Learning Face Super-Resolution With Facial Priors (CVPR 2018 · similarity 0.92)
- Super-FAN: Integrated Facial Landmark Localization and Super-Resolution of Real-World Low Resolution Faces in Arbitrary Poses With GANs (CVPR 2018 · similarity 0.89)
- Spatial-Frequency Mutual Learning for Face Super-Resolution (CVPR 2023 · similarity 0.89)
- Joint Super-Resolution and Alignment of Tiny Faces (AAAI 2020 · similarity 0.88)
- Low-Light Face Super-resolution via Illumination, Structure, and Texture Associated Representation (AAAI 2024 · similarity 0.87)
- Blind Face Restoration under Extreme Conditions: Leveraging 3D-2D Prior Fusion for Superior Structural and Texture Recovery (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.