让AI看图时定位并描述质量细节，提升图像评估精度
Grounding-IQA: Grounding Multimodal Language Model for Image Quality Assessment
- 通过定位+描述结合，实现图像局部质量细粒度评估
- 构建16万样本数据集，支持区域描述与问答双任务
- 适合需要精准图像质量分析的视觉质检场景
多模态大语言模型的发展使图像质量评估可基于自然语言描述实现，从而提供更细致的评价。然而，现有方法主要依赖通用上下文描述，难以实现精细评估。为此，本文提出一种新的图像质量评估范式—— grounding-IQA，将多模态指代与定位能力融入IQ A，实现更细粒度的质量感知。该范式包含两个子任务：GIQA-DES（带精确位置的详细描述）和GIQA-VQA（局部区域质量问答）。为支持该范式，我们通过自动化标注流程构建了16万样本的GIQA-160K数据集，并设计了涵盖描述质量、问答准确率与定位精度的GIQA-Bench基准。实验表明，该方法显著提升了图像质量评估的细粒度能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。