Scientific Image Quality Assessment via Multi-modal Retrieval-Augmented Generation
Published 18 Sept 2026arXiv:2609.19634
Updated 4 h ago · first seen 18 Sept 2026
paper_01M2SEGHBFCZTCDV12NV33K499
Abstract
This paper proposes a Retrieval-Augmented Generation (RAG) framework for scientific image quality assessment, designed to simultaneously address both the understanding track (SIQA-U) and the scoring track (SIQA-S) of the SIQA challenge. We construct a multimodal index that integrates textual semantics with fine-grained visual features, and develop a multi-route retrieval and fusion mechanism to provide large language models with highly relevant reference cases, thereby enhancing their capability to evaluate complex scientific images. Experimental results demonstrate that the proposed framework effectively aligns with the judgment criteria of human experts. Ultimately, our method achieves 1st place in the SIQA-U track of the SIQA challenge at the ICME 2026 Grand Challenges.
Organizations
Organizations 0
No organization stated. arXiv metadata does not carry affiliations; an organization is linked only when a model card or lab page cites the paper.
Models
Models introduced or described 0
Inbound described_by relations from model cards and documentation.
No model links this paper yet
Datasets
Datasets used 0
No dataset relation recorded.
Benchmarks
Benchmarks used 0
No benchmark relation recorded.
Code
Repositories & frameworks 0
No repository linked.
Timeline
Timeline 2
- Property changedPaperScientific Image Quality Assessment via Multi-modal Retrieval-Augmented Generation
Scientific Image Quality Assessment via Multi-modal Retrieval-Augmented Generation: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv New paper: Scientific Image Quality Assessment via Multi-modal Retrieval-Augmented Generation
arxiv
Sources
Sources 2
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.