Problem
Research questions and friction points this paper is trying to address.
image quality assessment
localization
degradation
perceived quality
fine-grained analysis
From Glance to Scrutiny: Progressive Distortion Reasoning for Fine-Grained Image Quality Assessment
🤖 AI Summary
本文提出GS-IQA框架，通过两阶段强化学习方法解决细粒度图像质量评估中失真定位、识别和严重性估计问题。
📝 Abstract
Multi-modal large language models (MLLMs) have demonstrated significant potential in image quality assessment (IQA) by bridging visual perception with descriptive evaluations. However, existing approaches mainly focus on holistic quality prediction, often functioning as black boxes that provide limited insight into where distortions occur and how they affect perceived quality, hindering fine-grained analysis of localized and heterogeneous degradations. We propose GS-IQA, a framework that reformulates IQA as a progressive Where--What--How diagnosis, emulating the human perceptual process from an initial glance to closer scrutiny. Since a severity judgment is meaningful only for a correctly localized and recognized region, we realize this progression through a two-stage reinforcement learning paradigm that respects such dependencies: the glance stage uses a perception-gated reward to establish where degradations lie and what they are, activating severity feedback only once both are correct, while the scrutiny stage introduces online reward-conditioned degradation generation to synthesize hard examples targeted at the model's perceptual bottlenecks, sharpening its discrimination of subtle severity variations. To enable systematic evaluation, we construct Diag-Bench, a region-level IQA benchmark of about 25K curated samples spanning 12 distortion types and five ordinal severity levels. Extensive experiments show that GS-IQA consistently surpasses state-of-the-art methods in distortion localization, recognition, and severity estimation, and that its diagnostic representations transfer effectively to conventional global quality prediction across diverse external benchmarks. Code and data will be released.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Progressive Distortion Reasoning
Reinforcement Learning
Degradation Localization and Recognition
Severity Estimation
Diagnostic Representations
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
