AI Paper Atlas

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

ICLR 2026 · Image generation › Image restoration · approach: Efficient restoration architectures · 3 citations (OpenAlex)

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 changedWhereMeasuredEffect
add task prompt pool (ablation)DATPRL-IR · Rain100L (6-task)PSNR: 38.34 -> 39.32Improved
add domain prompt pool (ablation)DATPRL-IR · Rain100L (6-task)PSNR: 38.34 -> 38.88Improved
add both task and domain pools (ablation)DATPRL-IR · Rain100L (6-task)PSNR: 38.34 -> 39.56Improved
add both pools (ablation)DATPRL-IR · AAPM CT denoising (6-task)PSNR: 33.70 -> 33.80Improved
replace domain prompt pool with explicit text prompt per domain (ablation)DATPRL-IR · GoPro deblurring (9-task)PSNR: 29.57 -> 29.31Hurt
replace domain prompt pool with simple learnable domain encoding (ablation)DATPRL-IR · GoPro deblurring (9-task)PSNR: 29.57 -> 29.21Hurt
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 / 26.82No clear effect
enlarge prompt pool from 15 to 20 (ablation)DATPRL-IR · 6-task averagePSNR: 30.77 -> 30.73No clear effect
use top-k 1 instead of 3/5 (ablation)DATPRL-IR · 6-task averagePSNR: 30.77 -> 30.48Hurt
train on 9 tasks instead of 6DATPRL-IR · 6-task average (original tasks)PSNR: 30.77 -> 30.78No clear effect
use domain-aware task prompt representation vs MoCEIRDATPRL-IR · RSI deblurring UCMerced (unseen)PSNR: 27.35 -> 28.91Improved
DATPRL-IR vs best baseline on real-world derainingDATPRL-IR · SPA-DataPSNR: 32.35 -> 32.32No 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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy