AI RESEARCH
From Concepts to Judgments: Interpretable Image Aesthetic Assessment
arXiv CS.CV
•
ArXi:2603.18108v1 Announce Type: new Image aesthetic assessment (IAA) aims to predict the aesthetic quality of images as perceived by humans. While recent IAA models achieve strong predictive performance, they offer little insight into the factors driving their predictions. Yet for users, understanding why an image is considered pleasing or not is as valuable as the score itself, motivating growing interest in interpretability within IAA. When humans evaluate aesthetics, they naturally rely on high-level cues to justify their judgments.