Refine-IQA: Multi-Stage Reinforcement Finetuning for Perceptual Image Quality Assessment
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909737379954688 |
|---|---|
| author | Jia, Ziheng Qian, Jiaying Zhang, Zicheng Chen, Zijian Min, Xiongkuo |
| author_facet | Jia, Ziheng Qian, Jiaying Zhang, Zicheng Chen, Zijian Min, Xiongkuo |
| contents | 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's rollouts but provide no reward supervision for the "think" process, leaving its correctness and efficacy uncontrolled. Furthermore, these methods typically fine-tune directly on downstream IQA tasks without explicitly enhancing the model's native low-level visual quality perception, which may constrain its performance upper bound. In response to these gaps, we propose the multi-stage RFT IQA framework (Refine-IQA). In Stage-1, we build the Refine-Perception-20K dataset (with 12 main distortions, 20,907 locally-distorted images, and over 55K RFT samples) and design multi-task reward functions to strengthen the model's visual quality perception. In Stage-2, targeting the quality scoring task, we introduce a probability difference reward involved strategy for "think" process supervision. The resulting Refine-IQA Series Models achieve outstanding performance on both perception and scoring tasks-and, notably, our paradigm activates a robust "think" (quality interpreting) capability that also attains exceptional results on the corresponding quality interpreting benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_03763 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Refine-IQA: Multi-Stage Reinforcement Finetuning for Perceptual Image Quality Assessment Jia, Ziheng Qian, Jiaying Zhang, Zicheng Chen, Zijian Min, Xiongkuo Computer Vision and Pattern Recognition Artificial Intelligence 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's rollouts but provide no reward supervision for the "think" process, leaving its correctness and efficacy uncontrolled. Furthermore, these methods typically fine-tune directly on downstream IQA tasks without explicitly enhancing the model's native low-level visual quality perception, which may constrain its performance upper bound. In response to these gaps, we propose the multi-stage RFT IQA framework (Refine-IQA). In Stage-1, we build the Refine-Perception-20K dataset (with 12 main distortions, 20,907 locally-distorted images, and over 55K RFT samples) and design multi-task reward functions to strengthen the model's visual quality perception. In Stage-2, targeting the quality scoring task, we introduce a probability difference reward involved strategy for "think" process supervision. The resulting Refine-IQA Series Models achieve outstanding performance on both perception and scoring tasks-and, notably, our paradigm activates a robust "think" (quality interpreting) capability that also attains exceptional results on the corresponding quality interpreting benchmark. |
| title | Refine-IQA: Multi-Stage Reinforcement Finetuning for Perceptual Image Quality Assessment |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2508.03763 |