Scientific Image Quality Assessment via Multi-modal Retrieval-Augmented Generation

A Retrieval-Augmented Generation framework for scientific image quality assessment took 1st place in the SIQA-U understanding track of the SIQA challenge at the ICME 2026 Grand Challenges, according to arXiv paper 2609.19634v1. The framework builds a multimodal index combining textual semantics with fine-grained visual features and uses a multi-route retrieval and fusion mechanism to supply large language models with relevant reference cases for evaluating complex scientific images. Experimental results showed the method aligned with human expert judgment criteria across both the SIQA-U understanding track and the SIQA-S scoring track.

arXiv:2609.19634v1 Announce Type: new 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.