IQA-Spider: Unifying Multi-Granularity Image Quality Assessment with Reasoning, Grounding and Referring 事件

IQA-Spider: Unifying Multi-Granularity Image Quality Assessment with Reasoning, Grounding and Referring arXiv:2605.24553v1 Announce Type: new Abstract: 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{