Research map / Image generation / Super-resolution
Cascaded Local Implicit Transformer for Arbitrary-Scale 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 the local implicit baseline with CLIT | EDSR-baseline arbitrary-scale SR · DIV2K validation ×2 | PSNR (dB): 34.72 -> 34.82 | Helped |
| use CLIT instead of LTE | RDN arbitrary-scale SR · DIV2K validation ×12 | PSNR (dB): 23.95 -> 24.01 | Helped |
| use CLIT instead of LTE | SwinIR arbitrary-scale SR · DIV2K validation ×30 | PSNR (dB): 20.73 -> 20.71 | Hurt |
| add cross-scale local attention (ablation) | LIT · DIV2K validation ×2 | PSNR (dB): 34.74 -> 34.79 | Helped |
| add cross-scale local attention (ablation) | LIT · DIV2K validation ×12 | PSNR (dB): 23.70 -> 23.79 | Helped |
| add cell size decoding (ablation) | LIT · DIV2K validation ×2 | PSNR (dB): 34.64 -> 34.79 | Helped |
| add cell size decoding (ablation) | LIT · DIV2K validation ×12 | PSNR (dB): 23.78 -> 23.79 | No clear effect |
| add local ensemble (ablation) | LIT · DIV2K validation ×2 | PSNR (dB): 34.79 -> 34.81 | Helped |
| vary local grid from 7×7 to 25×25 (ablation) | LIT · DIV2K validation ×2 | PSNR (dB): 34.79 -> 34.83 | Helped |
| vary local grid from 7×7 to 25×25 (ablation) | LIT · DIV2K validation ×12 | PSNR (dB): 23.79 -> 23.78 | No clear effect |
| train across r ∼ U(1, 12) rather than r ∼ U(1, 4) (ablation) | LIT · DIV2K validation ×2 and ×12 | PSNR (dB): 34.79 -> 34.72; 23.79 -> 23.83 | Mixed |
| use alternative small/large-scale training (ablation) | LIT · DIV2K validation ×2 and ×12 | PSNR (dB): 34.79 -> 34.75; 23.79 -> 23.84 | Mixed |
Closest papers by meaning
- HIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution (CVPR 2025 · similarity 0.87)
- Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary (CVPR 2024 · similarity 0.87)
- Recursive Generalization Transformer for Image Super-Resolution (ICLR 2024 · similarity 0.86)
- Effective Diffusion Transformer Architecture for Image Super-Resolution (AAAI 2025 · similarity 0.86)
- CFAT: Unleashing Triangular Windows for Image Super-resolution (CVPR 2024 · similarity 0.86)
- Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decoder (CVPR 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.