paper-with-me

홈 › Papers

ME-IQA: Memory-Enhanced Image Quality Assessment via Re-Ranking

2026-03-21 · Kanglong Fan, Tianhe Wu, Wen Wen, Jianzhao Liu, Le Yang, Yabin Zhang, Yiting Liao, Junlin Li, Li Zhang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.20785

Code (0)

등록된 구현이 없습니다.

Tasks

Image Quality Assessment

Similar Papers 제목 키워드 기반

Quality Assessment for Comparing Image Enhancement Algorithms

2014-06-01 · CVPR 2014 6 · Zhengying Chen, Tingting Jiang, Yonghong Tian

As the image enhancement algorithms developed in recent years, how to compare the performances of different image enhancement algorithms becomes a novel task. In this paper, we propose a framework to do quality assessmen…

Image EnhancementImage Quality AssessmentNR-IQA

HiLLIE: Human-in-the-Loop Training for Low-Light Image Enhancement

2025-05-04 · Xiaorui Zhao, Xinyue Zhou, Peibei Cao, Junyu Lou 외

Developing effective approaches to generate enhanced results that align well with human visual preferences for high-quality well-lit images remains a challenge in low-light image enhancement (LLIE). In this paper, we pro…

Image EnhancementImage Quality AssessmentLow-Light Image Enhancement

Rank-based No-reference Quality Assessment for Face Swapping

2024-06-04 · Xinghui Zhou, Wenbo Zhou, Tianyi Wei, Shen Chen 외

Face swapping has become a prominent research area in computer vision and image processing due to rapid technological advancements. The metric of measuring the quality in most face swapping methods relies on several dist…

Face SwappingImage Quality AssessmentNo-Reference Image Quality AssessmentNR-IQA

RMT-BVQA: Recurrent Memory Transformer-based Blind Video Quality Assessment for Enhanced Video Content

2024-05-14 · Tianhao Peng, Chen Feng, Duolikun Danier, Fan Zhang 외

With recent advances in deep learning, numerous algorithms have been developed to enhance video quality, reduce visual artifacts, and improve perceptual quality. However, little research has been reported on the quality …

Contrastive LearningVideo EnhancementVideo Quality AssessmentVisual Question Answering (VQA)

Underwater Ranker: Learn Which Is Better and How to Be Better

2022-08-14 · Chunle Guo, Ruiqi Wu, Xin Jin, Linghao Han 외

In this paper, we present a ranking-based underwater image quality assessment (UIQA) method, abbreviated as URanker. The URanker is built on the efficient conv-attentional image Transformer. In terms of underwater images…

Image EnhancementImage Quality AssessmentUIE