Uncertainty-guided Style-aware Perceptual Quality Assessment for AI-Generated Images

Tushar Shinde, Shivaanee Eswaran; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2025, pp. 3406-3414

In this paper, we propose a novel approach for perceptual quality assessment (PQA) of AI-generated images by incorporating style awareness and uncertainty-guided probabilistic modeling. The proposed method, Uncertainty-guided Style-aware Probabilistic Perceptual Quality Assessment (US-PPQA), takes advantage of the distinct characteristics of different image styles, such as anime and realistic, to improve quality predictions. We use the AGIQA-1K dataset, which contains 1080 AI-generated images across two styles, to train separate models that predict quality scores for each style. Additionally, we introduce a style classification model that estimates the probability of an image belonging to either style. The final quality score is then computed by combining the style-specific predictions, weighted by these probabilities. Furthermore, we incorporate uncertainty into the individual style quality score predictors and recompute the final score. The performance of our method is evaluated using standard correlation metrics (SRCC, KRCC, and PLCC). Our results demonstrate that the style-aware, uncertainty-guided model outperforms traditional methods, achieving improved rank accuracy in perceptual quality assessment for AI-generated content.