Research map / Image generation / Super-resolution
Implicit Transformer Network for Screen Content Image Continuous Super-Resolution
Jingyu Yang, Sheng Shen, Huanjing Yue, Kun Li
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 |
|---|---|---|---|
| add scale token and implicit position encoding together (ablation) | ITSRN-RDN · SCI1K x4 | PSNR (dB): 30.43 -> 30.82 | Improved |
| add scale token (ablation) | ITSRN-RDN · SCI1K x4 | PSNR (dB): 30.43 -> 30.60 | Improved |
| add implicit position encoding (ablation) | ITSRN-RDN · SCI1K x4 | PSNR (dB): 30.43 -> 30.76 | Improved |
| add scale token on top of IPE (ablation) | ITSRN-RDN · SCI1K x6 | PSNR (dB): 26.05 -> 26.00 | Mixed |
| add scale token and IPE (ablation) | ITSRN-RDN · SCI1K out-of-scale x6 | PSNR (dB): 25.94 -> 26.00 | Improved |
| learned IPE weights instead of fixed distance-based weights (ablation) | ITSRN-RDN · SCI1K-compression | PSNR (dB): 27.78 -> 28.02 at x4; 17.31 -> 17.29 at x40 | Mixed |
| train with scale range x2-x8 instead of x2-x4 (ablation) | ITSRN-RDN · SCI1K x8 | PSNR (dB): 23.16 -> 23.59 | Improved |
| train with scale range x2-x8 instead of x2-x4 (ablation) | ITSRN-RDN · SCI1K x4 | PSNR (dB): 30.82 -> 30.83 | No clear effect |
| replace LIIF concatenation MLP with implicit transformer plus IPE | RDN backbone continuous SR · SCI1K x4 | PSNR (dB): 30.55 -> 30.82 | Improved |
| ITSRN vs RCAN at x4 on uncompressed SCI1K | ITSRN-RDN · SCI1K x4 | PSNR (dB): 30.80 -> 30.82 | No clear effect |
Closest papers by meaning
- B-Spline Texture Coefficients Estimator for Screen Content Image Super-Resolution (CVPR 2023 · similarity 0.88)
- VarSR: Variational Super-Resolution Network for Very Low Resolution Images (ECCV 2020 · similarity 0.86)
- HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution (ECCV 2024 · similarity 0.85)
- IAFMNet: Information-Aware Feature Modulation for Efficient Super-Resolution (CVPR 2026 · similarity 0.85)
- Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary (CVPR 2024 · similarity 0.84)
- Recursive Generalization Transformer for Image Super-Resolution (ICLR 2024 · similarity 0.83)
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.
