Exploring AI in Fashion: A Review of Aesthetics, Personalization, Virtual Try-On, and Forecasting

Abstract

Fashion-focused artificial intelligence has rapidly advanced in recent years, driven by deep learning and its deployment in recommender systems, detection, retrieval, and analytics. Yet several consumer-facing domains remain comparatively under-surveyed despite their practical impact. This work provides a comprehensive review of methods, datasets, and evaluation metrics across four such domains: aesthetics, personalization, virtual try-on, and forecasting. We synthesize technical approaches spanning representation learning, preference modeling, image transformation, and time-series analysis; relate them to downstream recommender systems and user experience; and highlight cross-domain dependencies (e.g., aesthetics-informed personalization, trend-informed recommendations). We also catalog commonly used datasets and metrics, including those from object detection and image segmentation pipelines, where relevant to try-on and visual understanding. Finally, we identify open challenges and promising directions for integrated AI-driven fashion systems.

Figures (6)

• Figure 1: Integrated Fashion AI Framework showing domain interconnections and information flow between aesthetics, personalization, virtual try-on, and forecasting systems.
• Figure 2: Technical Architecture of Fashion AI Domains showing direct connections between aesthetics, personalization, virtual try-on, and forecasting systems with cross-domain learning pathways.
• Figure 3: Fashion Aesthetics framework for visual analysis and style recognition.
• Figure 4: Personalization framework for user-centric recommendations.
• Figure 5: Virtual Try-On framework for 3D fitting and size prediction.