Preference-Guided Debiasing for No-Reference Enhancement Image Quality Assessment
This addresses the generalization issue in image quality assessment for enhanced images, which is important for applications like photo editing and computer vision, but it is an incremental improvement over existing methods.
The paper tackles the problem of no-reference image quality assessment (NR-IQA) for enhanced images, which often overfits to specific enhancement algorithms, by proposing a preference-guided debiasing framework that removes algorithm-specific biases to focus on perceptual quality cues, resulting in superior robustness and cross-algorithm generalization on public benchmarks.
Current no-reference image quality assessment (NR-IQA) models for enhanced images often struggle to generalize, as they tend to overfit to the distinct patterns of specific enhancement algorithms rather than evaluating genuine perceptual quality. To address this issue, we propose a preference-guided debiasing framework for no-reference enhancement image quality assessment (EIQA). Specifically, we first learn a continuous enhancement-preference embedding space using supervised contrastive learning, where images generated by similar enhancement styles are encouraged to have closer representations. Based on this, we further estimate the enhancement-induced nuisance component contained in the raw quality representation and remove it before quality regression. In this way, the model is guided to focus on algorithm-invariant perceptual quality cues instead of enhancement-specific visual fingerprints. To facilitate stable optimization, we adopt a two-stage training strategy that first learns the enhancement-preference space and then performs debiased quality prediction. Extensive experiments on public EIQA benchmarks demonstrate that the proposed method effectively mitigates algorithm-induced representation bias and achieves superior robustness and cross-algorithm generalization compared with existing approaches.