AesRec: A Dataset for Aesthetics-Aligned Clothing Outfit Recommendation

TL;DR

AesRec introduces a comprehensive dataset with aesthetic annotations for clothing, enabling the development of recommendation systems that incorporate explicit aesthetic qualities to improve personalization and aesthetic alignment.

Contribution

The paper presents AesRec, a novel dataset with systematic aesthetic annotations at item and outfit levels, facilitating aesthetics-aware clothing recommendation models.

Findings

AesRec enables aesthetics-aligned recommendations with improved aesthetic guidance.

Large-scale aesthetic scoring validated through human-machine consistency.

Integrating aesthetic features enhances personalized clothing recommendations.

Abstract

Clothing recommendation extends beyond merely generating personalized outfits; it serves as a crucial medium for aesthetic guidance. However, existing methods predominantly rely on user-item-outfit interaction behaviors while overlooking explicit representations of clothing aesthetics. To bridge this gap, we present the AesRec benchmark dataset featuring systematic quantitative aesthetic annotations, thereby enabling the development of aesthetics-aligned recommendation systems. Grounded in professional apparel quality standards and fashion aesthetic principles, we define a multidimensional set of indicators. At the item level, six dimensions are independently assessed: silhouette, chromaticity, materiality, craftsmanship, wearability, and item-level impression. Transitioning to the outfit level, the evaluation retains the first five core attributes while introducing stylistic synergy, visual harmony, and outfit-level impression as distinct metrics to capture the collective aesthetic impact. Given the increasing human-like proficiency of Vision-Language Models in multimodal understanding and interaction, we leverage them for large-scale aesthetic scoring. We conduct rigorous human-machine consistency validation on a fashion dataset, confirming the reliability of the generated ratings. Experimental results based on AesRec further demonstrate that integrating quantified aesthetic information into clothing recommendation models can provide aesthetic guidance for users while fulfilling their personalized requirements.