Research map / Image generation / Super-resolution
UCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Prompt
Xin Li, Bingchen Li, Yeying Jin, Cuiling Lan, Hanxin Zhu, Yulin Ren, Zhibo Chen
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 dynamic prompt (DPM) to the token mixer instead of no prompt (ablation) | UCIP · Manga109, JPEG Q=40 | PSNR: 25.70 -> 26.11 | Improved |
| use fixed prompts instead of dynamic prompts (ablation) | UCIP · Manga109, JPEG Q=40 | PSNR: 25.70 -> 25.62 | Hurt |
| replace PromptIR-style prompts with DPM (ablation) | UCIP · Manga109, JPEG Q=40 | PSNR: 25.89 -> 26.11 with 9.66M -> 0.46M params | Improved |
| add local 3x3 conv branch to the token mixer (ablation) | UCIP · Manga109, JPEG Q=40 | PSNR: 25.97 -> 26.11 | Improved |
| increase number of dynamic prompts from 1 to 8 (ablation) | UCIP · Manga109, JPEG Q=40 | PSNR: 25.84 -> 26.11 | Improved |
| increase number of dynamic prompts from 8 to 16 (ablation) | UCIP · Manga109, JPEG Q=40 | PSNR: 26.11 -> 26.19 | Improved |
| UCIP vs transformer and MLP baselines across codecs | UCIP · UCSR Manga109, HM Q=32 | PSNR: 27.17 -> 27.61 (vs SwinIR) | Improved |
| UCIP vs MAXIM on SSIM-oriented codec at low quality | UCIP · UCSR Set5, C_SSIM Q=4 | PSNR: 23.78 -> 23.74 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PromptIR — PromptIR: Prompting for All-in-One Image Restoration (NeurIPS 2023) · better on 3 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration (ECCV 2024 · similarity 0.88)
- FIPER: Factorized Features for Robust Image Super-Resolution and Compression (NeurIPS 2025 · similarity 0.86)
- COMISR: Compression-Informed Video Super-Resolution (ICCV 2021 · similarity 0.86)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.84)
- CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution (CVPR 2025 · similarity 0.84)
- UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensing (ICML 2026 · similarity 0.84)
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.
