DR.Experts: Differential Refinement of Distortion-Aware Experts for Blind Image Quality Assessment

2026-02-10

AI Summary

Existing blind image quality assessment (BIQA) methods struggle to capture subtle distortions, leading to inconsistencies with human perception. This work proposes a prior-driven BIQA framework that explicitly models distortion priors for the first time and decouples distortion from semantic features through a distortion saliency differencing mechanism. By integrating a mixture-of-experts module with dynamic distortion-aware weighting, the method achieves perceptually aligned quality prediction. Extensive experiments demonstrate that the proposed approach achieves state-of-the-art performance across five mainstream BIQA benchmarks, significantly improving both generalization capability and data efficiency.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: State Estimation

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Blind Image Quality Assessment, aiming to replicate human perception of visual quality without reference, plays a key role in vision tasks, yet existing models often fail to effectively capture subtle distortion cues, leading to a misalignment with human subjective judgments. We identify that the root cause of this limitation lies in the lack of reliable distortion priors, as methods typically learn shallow relationships between unified image features and quality scores, resulting in their insensitive nature to distortions and thus limiting their performance. To address this, we introduce DR.Experts, a novel prior-driven BIQA framework designed to explicitly incorporate distortion priors, enabling a reliable quality assessment. DR.Experts begins by leveraging a degradation-aware vision-language model to obtain distortion-specific priors, which are further refined and enhanced by the proposed Distortion-Saliency Differential Module through distinguishing them from semantic attentions, thereby ensuring the genuine representations of distortions. The refined priors, along with semantics and bridging representation, are then fused by a proposed mixture-of-experts style module named the Dynamic Distortion Weighting Module. This mechanism weights each distortion-specific feature as per its perceptual impact, ensuring that the final quality prediction aligns with human perception. Extensive experiments conducted on five challenging BIQA benchmarks demonstrate the superiority of DR.Experts over current methods and showcase its excellence in terms of generalization and data efficiency.

Problem

• Blind Image Quality Assessment
• distortion priors
• human perception
• distortion cues
• quality assessment

Innovation

• Distortion-aware priors
• Differential refinement
• Vision-language model
• Dynamic Distortion Weighting
• Blind Image Quality Assessment