How Good Is Aesthetic Ability of a Fashion Model?
Xingxing Zou, Kaicheng Pang, Wen Zhang, Waikeung Wong
Abstract
We introduce A100 (Aesthetic 100) to assess the aesthetic ability of the fashion compatibility models. To date, it is the first work to address the AI model's aesthetic ability with detailed characterization based on the professional fashion domain knowledge. A100 has several desirable characteristics: 1. Completeness. It covers all types of standards in the fashion aesthetic system through two tests, namely LAT (Liberalism Aesthetic Test) and AAT (Academicism Aesthetic Test); 2. Reliability. It is training data agnostic and consistent with major indicators. It provides a fair and objective judgment for model comparison. 3. Explainability. Better than all previous indicators, the A100 further identifies essential characteristics of fashion aesthetics, thus showing the model's performance on more fine-grained dimensions, such as Color, Balance, Material, etc. Experimental results prove the advance of the A100 in the aforementioned aspects. All data can be found at https://github.com/AemikaChow/AiDLab- fAshIon-Data.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers2
- Garments2Look: A Multi-Reference Dataset for High-Fidelity Outfit-Level Virtual Try-On with Clothing and AccessoriesJunyao Hu, Zhongwei Cheng, Waikeung Wong, Xingxing ZouCVPR 2026 · 4 citations
- FashionSAP: Symbols and Attributes Prompt for Fine-Grained Fashion Vision-Language Pre-TrainingYunpeng Han, Lisai Zhang, Qingcai Chen, Zhijian Chen et al.CVPR 2023
Builds on2
Related papers
- FiNet: Compatible and Diverse Fashion Image InpaintingXintong Han, Zuxuan Wu, Weilin Huang, Matthew R. Scott et al.ICCV 2019 · 85 citations
- Can Vision-Language Models Assess Graphic Design Aesthetics? A Benchmark, Evaluation, and Dataset PerspectiveRuichuan An, Shizhao Sun, Danqing Huang, Mingxi Cheng et al.ICLR 2026 · 6 citations
- Deciphering Compatibility Relationships with Textual Descriptions via Extraction and ExplanationYu Wang, Zexue He, Zhankui He, Hao Xu et al.AAAI 2024 · 6 citations
- FANCY: Human-centered, Deep Learning-based Framework for Fashion Style AnalysisYoungseung Jeon, Seungwan Jin, Kyungsik HanWWW 2021 · 25 citations
- StyleMe: Towards Intelligent Fashion Generation with Designer StyleDi Wu, Zhiwang Yu, Nan Ma, Jianan Jiang et al.CHI 2023 · 52 citations
