Grounding-IQA: Grounding Multimodal Language Model for Image Quality Assessment
Zheng Chen, Xun Zhang, Wenbo Li, Renjing Pei, Fenglong Song, Xiongkuo Min, Xiaohong Liu, Xin Yuan
Abstract
The development of multimodal large language models (MLLMs) enables the evaluation of image quality through natural language descriptions. This advancement allows for more detailed assessments. However, these MLLM-based IQA methods primarily rely on general contextual descriptions, sometimes limiting fine-grained quality assessment. To address this limitation, we introduce a new image quality assessment (IQA) task paradigm, **grounding-IQA**. This paradigm integrates multimodal referring and grounding with IQA to realize more fine-grained quality perception, thereby extending existing IQA. Specifically, grounding-IQA comprises two subtasks: grounding-IQA-description (GIQA-DES) and visual question answering (GIQA-VQA). GIQA-DES involves detailed descriptions with precise locations (e.g., bounding boxes), while GIQA-VQA focuses on quality QA for local regions. To realize grounding-IQA, we construct a corresponding dataset, GIQA-160K, through our proposed automated annotation pipeline. Furthermore, we develop a well-designed benchmark, GIQA-Bench. The benchmark comprehensively evaluates the model grounding-IQA performance from three perspectives: description quality, VQA accuracy, and grounding precision. Experiments demonstrate that our proposed task paradigm, dataset, and benchmark facilitate the more fine-grained IQA application. Code will be made public.
BibTeX
@inproceedings{
chen2026groundingiqa,
title={Grounding-{IQA}: Grounding Multimodal Language Model for Image Quality Assessment},
author={Zheng Chen and Xun Zhang and Wenbo Li and Renjing Pei and Fenglong Song and Xiongkuo Min and Xiaohong Liu and Xin Yuan and Yong Guo and Yulun Zhang},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=yEpE0QPpf8}
}