Research map / Image generation / Image restoration
Beyond Degradation Redundancy: Contrastive Prompt Learning for All-in-One Image Restoration
Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu, Liqiang Nie
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 CPL (SPM + CPR) to PromptIR | PromptIR · Three-task AiOIR | PSNR (dB): 32.06 -> 32.78 | Improved |
| add CPL to PromptIR | PromptIR · Five-task AiOIR | PSNR (dB): 29.15 -> 30.55 | Improved |
| add CPL to PromptIR | PromptIR · Seven-task AiOIR | PSNR (dB): improving upon the PromptIR baseline by 1.42 dB | Improved |
| add CPL to PromptIR | PromptIR · WeatherBench real-world | PSNR (dB): 27.86 -> 30.35 | Improved |
| add CPL to PromptIR | PromptIR · CDD-11 composite | PSNR (dB): 25.90 -> 29.07 | Improved |
| add CPR on top of SPM (k=1) (ablation) | SPM · Three-task AiOIR | PSNR (dB): 32.48 -> 32.78 | Improved |
| increase top-k from 1 to 2 in SPM (no CPR) (ablation) | SPM · Three-task AiOIR | PSNR (dB): 32.48 -> 32.54 | Improved |
| increase top-k from 1 to 3 in SPM (ablation) | SPM · Three-task AiOIR | PSNR (dB): 32.54 -> 32.23 | Hurt |
| increase top-k from 1 to 2 in SPM (ablation) | SPM · Five-task AiOIR | PSNR (dB): 30.06 -> 29.68 | Hurt |
| increase top-k from 1 to 3 in SPM (ablation) | SPM · Five-task AiOIR | PSNR (dB): 30.06 -> 29.54 | Hurt |
| increase number of prompts from 5 to 15 in dense PromptIR (ablation) | PromptIR · CDD-11 composite | PSNR (dB): 25.90 -> 26.10 | No clear effect |
| increase number of prompts from 5 to 15 with CPL (ablation) | PromptIR+CPL · CDD-11 composite | PSNR (dB): 29.07 -> 29.85 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- PromptIR — PromptIR: Prompting for All-in-One Image Restoration (NeurIPS 2023) · better on 8 of 8 shared results
- AdaIR — AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation (ICLR 2025) · better on 2 of 2 shared results
- InstructIR — InstructIR: High-Quality Image Restoration Following Human Instructions (ECCV 2024) · better on 2 of 2 shared results
- OneRestore — OneRestore: A Universal Restoration Framework for Composite Degradation (ECCV 2024) · better on 1 of 1 shared result
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
- Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration (AAAI 2024 · similarity 0.90)
- UP-Restorer: When Unrolling Meets Prompts for Unified Image Restoration (AAAI 2025 · similarity 0.90)
- Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration (NeurIPS 2026 · similarity 0.89)
- Learning Where and What to Restore for Composite Image Restoration (NeurIPS 2026 · similarity 0.89)
- Debiased All-in-one Image Restoration with Task Uncertainty Regularization (AAAI 2025 · similarity 0.89)
- Controlling Vision-Language Models for Multi-Task Image Restoration (ICLR 2024 · similarity 0.88)
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.
