Research map / Image generation / Image restoration
PromptRestorer: A Prompting Image Restoration Method with Degradation Perception
Cong Wang, Jinshan Pan, Wei Wang, Jiangxin Dong, Mengzhu Wang, Yakun Ju, Junyang 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 |
|---|---|---|---|
| prompt with raw pre-trained degradation features (vs no conditional branch) (ablation) | PromptRestorer · GoPro ablation | PSNR: 30.138 -> 31.015 | Improved |
| prompt with raw pre-trained degradation features (vs learnable conditional branch) (ablation) | PromptRestorer · GoPro ablation | PSNR: 30.646 -> 31.015 | Improved |
| add local prompting perceptor L2P (ablation) | PromptRestorer · GoPro ablation | PSNR: 30.819 -> 31.015 | Improved |
| add global prompting perceptor G2P (ablation) | PromptRestorer · GoPro ablation | PSNR: 30.697 -> 31.015 | Improved |
| add gated degradation perception propagation (ablation) | PromptRestorer · GoPro ablation | PSNR: 30.924 -> 31.015 | Improved |
| add Q-InAtt in G2P (ablation) | PromptRestorer · GoPro ablation | PSNR: 30.914 -> 31.015 | Improved |
| add KV-InAtt in G2P (ablation) | PromptRestorer · GoPro ablation | PSNR: 30.906 -> 31.015 | Improved |
| PromptRestorer vs Restormer on deraining average | Restormer · Deraining average | PSNR: 33.96 -> 34.05 | Improved |
| PromptRestorer vs Restormer on dehazing SOTS-Indoor (MAXIM best prior) | MAXIM · SOTS-Indoor | PSNR: 38.11 -> 42.54 | Improved |
| PromptRestorer vs Restormer on CSD desnowing | Restormer · CSD | PSNR: 35.43 -> 37.48 | Improved |
| PromptRestorer vs Restormer on real-world RealBlur-J | Restormer · RealBlur-J | PSNR: 28.96 -> 28.82 | Hurt |
| PromptRestorer vs DeHamer on Dense-Haze | DeHamer · Dense-Haze | PSNR: 16.62 -> 15.86 | Hurt |
Later papers that compared with this method
2 later accepted papers report PromptRestorer as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Boosting Filter Optimization and Prompt-Guided Decoding for Mixed Degradation Image Restoration (IJCV 2026 · better on 2 of 2 shared results)
- Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restoration (ECCV 2024 · better on 1 of 1 shared result)
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.
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 8 of 11 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
- DDR: Exploiting Deep Degradation Response as Flexible Image Descriptor (NeurIPS 2024 · similarity 0.90)
- UP-Restorer: When Unrolling Meets Prompts for Unified Image Restoration (AAAI 2025 · similarity 0.90)
- Controlling Vision-Language Models for Multi-Task Image Restoration (ICLR 2024 · similarity 0.89)
- Intra and Inter Parser-Prompted Transformers for Effective Image Restoration (AAAI 2025 · similarity 0.89)
- SelfPromer: Self-Prompt Dehazing Transformers with Depth-Consistency (AAAI 2024 · similarity 0.88)
- Dual Prompting Image Restoration with Diffusion Transformers (CVPR 2025 · similarity 0.87)
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.
