K-Hairstyle: A Large-scale Korean Hairstyle Dataset for Virtual Hair Editing and Hairstyle Classification
arXiv:2102.06288 · doi:10.1109/ICIP42928.2021.9506557
Abstract
The hair and beauty industry is a fast-growing industry. This led to the development of various applications, such as virtual hair dyeing or hairstyle transfer, to satisfy the customer's needs. Although several hairstyle datasets are available for these applications, they often consist of a relatively small number of images with low resolution, thus limiting their performance on high-quality hair editing. In response, we introduce a novel large-scale Korean hairstyle dataset, K-hairstyle, containing 500,000 high-resolution images. In addition, K-hairstyle includes various hair attributes annotated by Korean expert hairstylists as well as hair segmentation masks. We validate the effectiveness of our dataset via several applications, such as hair dyeing, hairstyle transfer, and hairstyle classification. K-hairstyle is publicly available at https://psh01087.github.io/K-Hairstyle/.
arXiv commentICIP 2021 final version
References in corpus (5)
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Wide Residual Networks
- Pyramid Attention Network for Semantic Segmentation
- StarGAN v2: Diverse Image Synthesis for Multiple Domains
- Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval