发表机构
School of Computer Science, Northwestern Polytechnical University; The Hong Kong University of Science and Technology（西北工业大学计算机科学学院; 香港科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对开放世界图像质量评估难题，提出IQA-T1框架，通过自主调用工具生成视觉证据增强多模态大语言模型推理，构建Q-Tool数据集，实验表明该框架性能最佳且评估可解释、基于证据。
AI 中文摘要
在开放世界环境中，图像质量评估（IQA）因泛化性和可解释性有限而仍具挑战性。基于多模态大语言模型（MLLMs）的近期方法引入文本推理进行质量预测，但判断严重依赖语义偏差的内部表示，对低级感知退化不敏感。我们提出IQA-T1，一个基于工具的视觉证据推理框架，用明确感知观察增强MLLM推理。推理时，模型自主调用专门分析工具生成结构化视觉证据，如噪声残差图、梯度统计和频谱，并逐步融入推理过程。为支持此范式，构建了Q-Tool数据集，含11k基于工具生成证据的多模态推理链。在七个IQA基准上的大量实验表明，IQA-T1在各数据集上实现最佳整体性能，同时产生可解释且基于证据的质量评估。代码和数据集可通过链接获取。
英文摘要
Image Quality Assessment (IQA) in open-world environments remains challenging due to limited generalization and interpretability. Recent approaches based on multimodal large language models (MLLMs) introduce textual reasoning for quality prediction, yet their judgments rely heavily on semantically biased internal representations, making them insensitive to low-level perceptual degradations. We propose IQA-T1, a tool-based visual evidence reasoning framework that augments MLLM reasoning with explicit perceptual observations. During inference, the model autonomously invokes specialized analysis tools to generate structured visual evidence, such as noise residual maps, gradient statistics, and frequency spectra, which are progressively integrated into the reasoning process. To support this paradigm, we construct Q-Tool, a dataset containing 11k multimodal reasoning chains grounded in tool-generated evidence. Extensive experiments on seven IQA benchmarks show that IQA-T1 achieves the best overall performance across datasets while producing interpretable and evidence-grounded quality assessments. Code and dataset are available at https://github.com/zibuyu-02/IQA-T1.
CommentsAccepted by ECCV 2026
