🔎 AIGC Detection

📷 CVPR2026 · 1 paper notes

Fine-grained Image Aesthetic Assessment: Learning Discriminative Scores from Relative Ranks

This paper introduces a new task of "fine-grained image aesthetic assessment," constructs the FGAesthetics benchmark containing 32,217 images across 10,028 series, and proposes FGAesQ: a model that learns discriminative aesthetic scores from relative rankings via Difference-Preserving Tokenization (DiffToken), Contrastive Text-Guided Alignment (CTAlign), and Ranking-Aware Regression (RankReg). The model achieves 0.779 pairwise accuracy on fine-grained scenes while maintaining a coarse-grained SRCC of 0.770.