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 GitHub.
Blogger's Review: IQA-T1 significantly enhances the accuracy and interpretability of image quality assessment by incorporating tool-generated visual evidence. This approach addresses the shortcomings of traditional MLLMs in processing low-level visual features and provides a novel perspective for future multimodal reasoning, holding substantial practical value and research significance.