ME-IQA: Memory-Enhanced Image Quality Assessment via Re-Ranking
arXiv:2603.20785
The paper introduces ME‑IQA, a test‑time memory‑enhanced re‑ranking framework that leverages a memory bank of reasoning summaries to retrieve similar images, converts a vision‑language model into a probabilistic comparator, and fuses pairwise preference probabilities with the original IQA score to produce finer, distortion‑sensitive quality predictions.
Abstract
Reasoning-induced vision-language models (VLMs) advance image quality assessment (IQA) with textual reasoning, yet their scalar scores often lack sensitivity and collapse to a few values, so-called discrete collapse. We introduce ME-IQA, a plug-and-play, test-time memory-enhanced re-ranking framework. It (i) builds a memory bank and retrieves semantically and perceptually aligned neighbors using reasoning summaries, (ii) reframes the VLM as a probabilistic comparator to obtain pairwise preference probabilities and fuse this ordinal evidence with the initial score under Thurstone's Case V model, and (iii) performs gated reflection and consolidates memory to improve future decisions. This yields denser, distortion-sensitive predictions and mitigates discrete collapse. Experiments across multiple IQA benchmarks show consistent gains over strong reasoning-induced VLM baselines, existing non-reasoning IQA methods, and test-time scaling alternatives.
Published as a conference paper at ECCV 2026