Research map / Image generation / Super-resolution
Journey Towards Tiny Perceptual Super-Resolution
Royson Lee, Łukasz Dudziak, Mohamed Abdelfattah, Stylianos I. Venieris, Hyeji Kim, Hongkai Wen, Nicholas D. Lane
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 |
|---|---|---|---|
| compare TPSR-D2 (searched discriminator, tiny generator) against SRGAN | TPSR x4 · Set5 | LPIPS: 0.0878 -> 0.076 | Improved |
| compare TPSR-D2 against EnhanceNet | TPSR x4 · Set5 | LPIPS: 0.1039 -> 0.076 | Improved |
| compare TPSR-D2 against EnhanceNet on PSNR | TPSR x4 · Set5 | PSNR: 28.51 -> 29.60 | Improved |
| compare TPSR-D2 against ESRGAN | TPSR x4 · Set5 | LPIPS: 0.076 -> 0.0745 | Hurt |
| compare TPSR-D2 against FEQE on distortion | TPSR x4 · Set5 | PSNR: 29.60 -> 31.29 | Hurt |
| compare TPSR-D2 against FEQE on perceptual metric | TPSR x4 · Set5 | LPIPS: 0.0912 -> 0.076 | Improved |
| use NAS-searched discriminators (D1, D2, D3) instead of SRGAN, ESRGAN and JAGAN discriminators (ablation) | TPSR generator · weighted average of test benchmarks | LPIPS | Improved |
| search discriminator with LPIPS reward instead of no-reference NIQE/PI (ablation) | discriminator search · DIV2K proxy task | search stability | Improved |
| initialize final generator training with shared weight cache (ablation) | TPSR generator · DIV2K | PSNR | Improved |
Closest papers by meaning
- SRFeat: Single Image Super-Resolution with Feature Discrimination (ECCV 2018 · similarity 0.91)
- SeD: Semantic-Aware Discriminator for Image Super-Resolution (CVPR 2024 · similarity 0.89)
- Exploring Semantic Feature Discrimination for Perceptual Image Super-Resolution and Opinion-Unaware No-Reference Image Quality Assessment (CVPR 2025 · similarity 0.89)
- Auto-Encoded Supervision for Perceptual Image Super-Resolution (CVPR 2025 · similarity 0.88)
- Uncertainty-Aware GAN for Single Image Super Resolution (AAAI 2024 · similarity 0.88)
- GSDD: Generative Space Dataset Distillation for Image Super-resolution (AAAI 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.
