Aesthetic Style Transfer in Large-Scale Art Datasets Using Deep Learning Models
Jing Xie, Kun Xie, Zhaoqin Lin · 2025
Deep learning algorithms that focus on image the artistic style migration process have increased interest in AI aesthetics. The study investigates aesthetic the artistic style migration process techniques for large art collections, from traditional to cutting-edge machine-based visual learning models. The review covers key advances in neural the artistic style migration process, adaptive instance normalization, and generative adversarial networks that change artistic styles across collections. This work evaluates large datasets and artistic variety issues and model generalization methodologies. the analysis is finalized by a critical examination of current limits and recommendations for research on direct transfer performance, user-directed creative customisation, and multiple data learning systems.