AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

Multi-Agent Image Restoration

Xu Jiang, Gehui Li, Bin Chen, Jian Zhang

IJCV 2026 · Multi-agent systems and games › LLM agents · approach: Robust and efficient agent execution · 27 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 three-stage framework to the scheduler (ablation)MAIR · Real-world pairedPSNR: 21.05 -> 21.67Improved
add three-stage framework to the scheduler (ablation)MAIR · Real-world pairedNIQE: 5.30 -> 5.25Improved
add intelligent tool selection by expert agents (ablation)MAIR · Group BPSNR: 20.14 -> 20.92Improved
add intelligent tool selection by expert agents (ablation)MAIR · Group BMUSIQ: 50.93 -> 60.98Improved
use multi-agent design instead of single agent (ablation)MAIR · Group BPSNR: 20.25 -> 20.92Improved
use multi-agent design instead of single agent (ablation)MAIR · Group Btokens: 2410 -> 883Improved
add summarized experience for planning (ablation)MAIR · Real-world pairedPSNR: 20.99 -> 21.67Improved
add summarized experience for planning (ablation)MAIR · Real-world pairedFID: 120.66 -> 115.61Improved
use MAIR instead of AgenticIRAgenticIR · Real-world paired and unpairedrunning time: 63.04 -> 35.42Improved

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