IQA-Spider：统一多粒度图像质量评估与推理、定位和指代
IQA-Spider: Unifying Multi-Granularity Image Quality Assessment with Reasoning, Grounding and Referring
AI总结：
提出IQA-Spider框架，通过统一推理、定位和指代任务，实现多粒度图像质量评估，并采用两阶段设计解决现有方法仅支持部分感知维度的问题。
摘要：
我们提出IQA-Spider，这是第一个将推理、定位和指代统一到单个基于LMM的框架中的图像质量评估（IQA）框架，用于多粒度质量理解。现有的基于LMM的IQA方法通常仅支持部分感知维度，例如质量描述和问答（即推理）或像素级定位。这一局限性主要源于缺乏（i）统一的任务和数据形式化，以及（ii）有效的多粒度学习优化范式。为解决这些局限性，我们形式化了一个严格的任务四元组，涵盖全局和局部质量描述、像素级定位以及区域级指代。基于这一形式化，我们通过可扩展的自动标注流水线构建了相应的IQA数据集，从而为统一的多粒度学习提供了坚实基础。为进一步实现统一感知，我们采用无冲突的两阶段设计，逐步将文本级多粒度理解扩展到像素级定位：（i）第一阶段使模型具备跨多个IQA任务的细粒度文本级推理能力；（ii）第二阶段引入无需训练的文本到点定位范式，通过将token logits映射到空间坐标来桥接文本语义和像素级感知。基于这些努力，我们实现了具有统一多粒度可解释图像质量评估的IQA-Spider。在多个基准上的大量实验展示了强大的性能，验证了所提出形式化和框架的有效性与通用性。
英文摘要：
We present IQA-Spider, the first image quality assessment (IQA) framework that unifies reasoning, grounding, and referring into a single LMM-based framework for multi-granularity quality understanding. Existing LMM-based IQA methods typically support only partial perception dimensions, such as quality description and question answering~(\textit{i.e.}, reasoning) or pixel-level grounding. This limitation largely stems from the absence of (i) a unified task and data formulation and (ii) effective optimization paradigms for multi-granularity learning. To address these limitations, we formulate a rigorous four-task paradigm covering global and local quality description, pixel-level grounding, and region-level referring. Based on this formulation, we construct a corresponding IQA dataset with a scalable and automatic annotation pipeline, thereby providing a solid foundation for unified multi-granularity learning. To further enable unified perception, we adopt a conflict-free two-stage design that progressively extends text-level multi-granularity understanding to pixel-level grounding: (i) the first stage equips the model with fine-grained text-level reasoning across multiple IQA tasks, and (ii) the second stage introduces a training-free text-to-point grounding paradigm, which bridges textual semantics and pixel-level perception by mapping token logits to spatial coordinates. Based on these efforts, we achieve IQA-Spider with unified multi-granularity explainable image quality assessment. Extensive experiments across multiple benchmarks demonstrate strong performance, validating the effectiveness and versatility of the proposed formulation and framework.
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。
