arXiv 2411.172372026-03-01cs.CV

Grounding-IQA: 多模态语言模型的接地图像质量评估

Grounding-IQA: Grounding Multimodal Language Model for Image Quality Assessment

Shanghai Jiao Tong University（上海交通大学）；Joy Future Academy（京东探索研究院）；Huawei Noah’s Ark Lab（华为诺亚实验室）；Westlake University（西湖大学）；Huawei（华为）

Zheng Chen, Xun Zhang, Wenbo Li, Renjing Pei, Fenglong Song, Xiongkuo Min, Xiaohong Liu, Xin Yuan, Yong Guo, Yulun Zhang

备注：: Accepted to ICLR 2026. Code is available at: https://github.com/zhengchen1999/Grounding-IQA

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出grounding-IQA任务范式，通过结合多模态指称与图像质量评估，实现更细粒度的图像质量感知。

摘要：

多模态大语言模型（MLLMs）的发展使得通过自然语言描述来评估图像质量成为可能。这一进展允许更详细的评估。然而，这些基于MLLMs的图像质量评估（IQA）方法主要依赖于一般的上下文描述，有时会限制细粒度的质量评估。为了解决这一限制，我们引入了一个新的图像质量评估（IQA）任务范式，即**grounding-IQA**。该范式将多模态指称和接地与IQA结合，以实现更细粒度的质量感知，从而扩展现有的IQA。具体而言，grounding-IQA包含两个子任务：grounding-IQA描述（GIQA-DES）和视觉问答（GIQA-VQA）。GIQA-DES涉及带有精确位置（例如边界框）的详细描述，而GIQA-VQA则专注于局部区域的质量问答。为了实现grounding-IQA，我们通过我们提出的自动化标注流程构建了一个相应的数据集GIQA-160K。此外，我们开发了一个精心设计的基准测试GIQA-Bench。该基准测试从三个角度评估grounding-IQA的性能：描述质量、VQA准确性以及接地精度。实验表明，我们提出的方法促进了更细粒度的IQA应用。代码：https://github.com/zhengchen1999/Grounding-IQA

英文摘要：

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 evaluates the grounding-IQA performance from three perspectives: description quality, VQA accuracy, and grounding precision. Experiments demonstrate that our proposed method facilitates the more fine-grained IQA application. Code: https://github.com/zhengchen1999/Grounding-IQA.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。