EUVIMEDEUVIMED entdecken
Crossref

UQ-Bench: A Benchmark for Evaluating Multimodal LLMs on Underwater Image Quality Assessment

Jingchao Cao, Guo An, Feng Gao, Ke Gu, Yutao Liu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (4) · 2589-2597

DOI: 10.1609/aaai.v40i4.37246 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jingchao Cao und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Despite the rapid progress of multimodal large language models (MLLMs), their capacity for low-level visual perception in underwater environments remains underexplored. To address this gap, we present UQ-Bench, the first systematically designed benchmark for evaluating the ability of MLLMs to perceive and assess underwater image quality at the low-level visual attribute level. UQ-Bench comprises three components: (1) UW-Perception, a dataset of 3,000 underwater images paired with targeted questions on key degradations such as color cast, blur, contrast, and exposure, covering both global and local perceptual dimensions; (2) UW-Describe, a dataset of 500 images with expert-annotated gold-standard descriptions for assessing the accuracy of model-generated text; and (3) UW-Eval, an evaluation protocol employing human mean opinion scores (MOS) for quantitative quality assessment. To ensure rigorous and reproducible benchmarking, we propose a GPT-assisted evaluation framework that aligns model outputs with expert references and enables fine-grained analysis of distortion perception. Experimental results demonstrate that while MLLMs exhibit preliminary competence in underwater low-level visual tasks, they still fall short in capturing subtle degradations and achieving human-level consistency, highlighting the need for further advances in foundation models for marine vision.

Zitieren

APA

Cao, J., An, G., Gao, F., Gu, K., & Liu, Y. (2026). UQ-Bench: A Benchmark for Evaluating Multimodal LLMs on Underwater Image Quality Assessment. Proceedings of the AAAI Conference on Artificial Intelligence, 40(4), 2589-2597. https://doi.org/10.1609/aaai.v40i4.37246

Vancouver

Cao J, An G, Gao F, Gu K, Liu Y. UQ-Bench: A Benchmark for Evaluating Multimodal LLMs on Underwater Image Quality Assessment. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(4):2589-2597. doi:10.1609/aaai.v40i4.37246

BibTeX
@article{Cao2026,
  author = {Cao, Jingchao and An, Guo and Gao, Feng and Gu, Ke and Liu, Yutao},
  title = {UQ-Bench: A Benchmark for Evaluating Multimodal LLMs on Underwater Image Quality Assessment},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {4},
  pages = {2589--2597},
  doi = {10.1609/aaai.v40i4.37246}
}
Kostenlos starten →