Refine-IQA: Multi-Stage Reinforcement Finetuning for Perceptual Image Quality Assessment

Ziheng Jia; Jiaying Qian; Zicheng Zhang; Zijian Chen; Xiongkuo Min

AAAI 2026technical0 citations

Refine-IQA: Multi-Stage Reinforcement Finetuning for Perceptual Image Quality Assessment

Ziheng Jia, Jiaying Qian, Zicheng Zhang, Zijian Chen, Xiongkuo Min

Abstract

Reinforcement fine-tuning (RFT) is a proliferating paradigm for LMM training. Analogous to high-level reasoning tasks, RFT is similarly applicable to low-level vision domains, including image quality assessment (IQA). Existing RFT-based IQA methods typically use rule-based output rewards to verify the model

BibTeX

@inproceedings{aaai2026_refineiqamultist,
  title = {Refine-IQA: Multi-Stage Reinforcement Finetuning for Perceptual Image Quality Assessment},
  author = {Ziheng Jia and Jiaying Qian and Zicheng Zhang and Zijian Chen and Xiongkuo Min},
  booktitle = {AAAI 2026},
  year = {2026}
}