Multi-Granularity Reasoning for Image Quality Assessment via Attribute-Aware Reinforcement Learning to Rank
About
Recent advances in reasoning-induced image quality assessment (IQA) have demonstrated the power of reinforcement learning to rank (RL2R) for training vision-language models (VLMs) to assess perceptual quality. However, existing approaches operate at a single granularity, predicting only an overall quality score, while overlooking the multi-dimensional nature of human quality perception, which encompasses attributes such as sharpness, color fidelity, noise level, and compositional aesthetics. In this paper, we propose MG-IQA (Multi-Granularity IQA), a multi-granularity reasoning framework that extends RL2R to jointly assess overall image quality and fine-grained quality attributes within a single inference pass. Our approach introduces three key innovations: (1) an attribute-aware prompting strategy that elicits structured multi-attribute reasoning from VLMs; (2) a multi-dimensional Thurstone reward model that computes attribute-specific fidelity rewards for group relative policy optimization; and (3) a cross-domain alignment mechanism that enables stable joint training across synthetic distortion, authentic distortion, and AI-generated image datasets without perceptual scale re-alignment. Extensive experiments on eight IQA benchmarks demonstrate that MG-IQA consistently outperforms state-of-the-art methods in both overall quality prediction (average SRCC improvement of 2.1\%) and attribute-level assessment, while generating interpretable, human-aligned quality descriptions.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Image Quality Assessment | SPAQ | SRCC0.841 | 250 | |
| Image Quality Assessment | AGIQA-3K | SRCC0.824 | 131 | |
| Image Quality Assessment | KonIQ-10k | SRCC0.83 | 126 | |
| Image Quality Assessment | KonIQ | SRCC0.848 | 119 | |
| Blind Image Quality Assessment | BID | SRCC0.795 | 63 | |
| Image Quality Assessment | CLIVE | SRCC0.846 | 54 | |
| Image Quality Assessment | AGIQA | SRCC0.842 | 28 | |
| Image Quality Assessment | Liu 13 | SRCC0.826 | 17 | |
| Image Quality Assessment | SRIQA | SRCC0.651 | 17 | |
| Image Quality Assessment | Min 19 | SRCC0.81 | 17 |