Papers › Complexity Experts are Task-Discriminative Learners for Any Image Restoration

Complexity Experts are Task-Discriminative Learners for Any Image Restoration

27 Nov 2024CVPR 2025 1arXiv:2411.18466archive 2025-07-28

Eduard Zamfir, Zongwei Wu, Nancy Mehta, Yuedong Tan, Danda Pani Paudel, Yulun Zhang, Radu Timofte

Recent advancements in all-in-one image restoration models have revolutionized the ability to address diverse degradations through a unified framework. However, parameters tied to specific tasks often remain inactive for other tasks, making mixture-of-experts (MoE) architectures a natural extension. Despite this, MoEs often show inconsistent behavior, with some experts unexpectedly generalizing across tasks while others struggle within their intended scope. This hinders leveraging MoEs' computational benefits by bypassing irrelevant experts during inference. We attribute this undesired behavior to the uniform and rigid architecture of traditional MoEs. To address this, we introduce ``complexity experts" -- flexible expert blocks with varying computational complexity and receptive fields. A key challenge is assigning tasks to each expert, as degradation complexity is unknown in advance. Thus, we execute tasks with a simple bias toward lower complexity. To our surprise, this preference effectively drives task-specific allocation, assigning tasks to experts with the appropriate complexity. Extensive experiments validate our approach, demonstrating the ability to bypass irrelevant experts during inference while maintaining superior performance. The proposed MoCE-IR model outperforms state-of-the-art methods, affirming its efficiency and practical applicability. The source will be publicly made available at \href{https://eduardzamfir.github.io/moceir/}{\texttt{eduardzamfir.github.io/MoCE-IR/}}

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

AttributeBlind All-in-One Image RestorationImage RestorationMixture-of-Experts

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Blind All-in-One Image Restoration 3-Degradations MoCE-IR Average PSNR 32.73 #2 of 9 Archive leaderboard report
Blind All-in-One Image Restoration 3-Degradations MoCE-IR SSIM 0.917 #2 of 9 Archive leaderboard report
Blind All-in-One Image Restoration 5-Degradations MoCE-IR Average PSNR 30.58 #2 of 9 Archive leaderboard report
Blind All-in-One Image Restoration 5-Degradations MoCE-IR SSIM 0.919 #2 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections