Research map / Image generation / Super-resolution
CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale 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 |
|---|---|---|---|
| Use CiaoSR instead of LTE with the same RDN backbone | RDN arbitrary-scale SR · Urban100, ×4 | PSNR (dB): 26.81 -> 27.11 | Helped |
| Use CiaoSR instead of LTE with the same RDN backbone | RDN arbitrary-scale SR · Urban100, ×8 | PSNR (dB): 22.88 -> 23.13 | Helped |
| Add learnable attention-in-attention in place of MLP-predicted ensemble weights (ablation) | CiaoSR with RDN · Urban100, ×4 | PSNR (dB): 26.69 -> 26.96 | Helped |
| Add scale-aware non-local attention (ablation) | CiaoSR with RDN · Urban100, ×4 | PSNR (dB): 26.96 -> 27.11 | Helped |
| Add learnable attention-in-attention in place of MLP-predicted ensemble weights (ablation) | CiaoSR with RDN · Urban100, ×8 | PSNR (dB): 22.80 -> 22.98 | Helped |
| Add scale-aware non-local attention (ablation) | CiaoSR with RDN · Urban100, ×8 | PSNR (dB): 22.98 -> 23.13 | Helped |
| Train across continuous scales instead of discrete scales {2, 3, 4} (ablation) | CiaoSR with RDN · Urban100, ×4 | PSNR (dB): 27.02 -> 27.11 | Helped |
| Train across continuous scales instead of scale {4} only (ablation) | CiaoSR with RDN · Urban100, ×4 | PSNR (dB): 26.88 -> 27.11 | Helped |
| Synthesize ×12 in one step instead of multiple steps (ablation) | CiaoSR with RDN · Urban100, ×12 | PSNR: 21.28 -> 21.42 | Helped |
Closest papers by meaning
- HIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution (CVPR 2025 · similarity 0.90)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.88)
- Efficient Attention-Sharing Information Distillation Transformer for Lightweight Single Image Super-Resolution (AAAI 2025 · similarity 0.86)
- Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary (CVPR 2024 · similarity 0.86)
- GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution (AAAI 2025 · similarity 0.86)
- Recursive Generalization Transformer for Image Super-Resolution (ICLR 2024 · 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.