Research map / Image generation / Image restoration
Learning Domain-Aware Task Prompt Representations for Multi-Domain All-in-One Image Restoration
Guanglu Dong, Chunlei Li, Chao Ren, Jingliang Hu, Yilei Shi, Xiao Xiang Zhu, Lichao Mou
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 task prompt pool (ablation) | DATPRL-IR · Rain100L (6-task) | PSNR: 38.34 -> 39.32 | Improved |
| add domain prompt pool (ablation) | DATPRL-IR · Rain100L (6-task) | PSNR: 38.34 -> 38.88 | Improved |
| add both task and domain pools (ablation) | DATPRL-IR · Rain100L (6-task) | PSNR: 38.34 -> 39.56 | Improved |
| add both pools (ablation) | DATPRL-IR · AAPM CT denoising (6-task) | PSNR: 33.70 -> 33.80 | Improved |
| replace domain prompt pool with explicit text prompt per domain (ablation) | DATPRL-IR · GoPro deblurring (9-task) | PSNR: 29.57 -> 29.31 | Hurt |
| replace domain prompt pool with simple learnable domain encoding (ablation) | DATPRL-IR · GoPro deblurring (9-task) | PSNR: 29.57 -> 29.21 | Hurt |
| swap MLLM for domain descriptions (LLaVA-7B to 13B or Qwen3-VL-2B) (ablation) | DATPRL-IR · RICE1 dehazing (9-task) | PSNR: 26.94 -> 26.92 / 26.82 | No clear effect |
| enlarge prompt pool from 15 to 20 (ablation) | DATPRL-IR · 6-task average | PSNR: 30.77 -> 30.73 | No clear effect |
| use top-k 1 instead of 3/5 (ablation) | DATPRL-IR · 6-task average | PSNR: 30.77 -> 30.48 | Hurt |
| train on 9 tasks instead of 6 | DATPRL-IR · 6-task average (original tasks) | PSNR: 30.77 -> 30.78 | No clear effect |
| use domain-aware task prompt representation vs MoCEIR | DATPRL-IR · RSI deblurring UCMerced (unseen) | PSNR: 27.35 -> 28.91 | Improved |
| DATPRL-IR vs best baseline on real-world deraining | DATPRL-IR · SPA-Data | PSNR: 32.35 -> 32.32 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PromptIR — PromptIR: Prompting for All-in-One Image Restoration (NeurIPS 2023) · better on 3 of 3 shared results
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 2 of 3 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
- Debiased All-in-one Image Restoration with Task Uncertainty Regularization (AAAI 2025 · similarity 0.89)
- UP-Restorer: When Unrolling Meets Prompts for Unified Image Restoration (AAAI 2025 · similarity 0.88)
- Controlling Vision-Language Models for Multi-Task Image Restoration (ICLR 2024 · similarity 0.87)
- Intra and Inter Parser-Prompted Transformers for Effective Image Restoration (AAAI 2025 · similarity 0.86)
- Domain-Controlled Prompt Learning (AAAI 2024 · similarity 0.86)
- Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration (NeurIPS 2026 · 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.
