Ukiyo-e Analysis and Creativity with Attribute and Geometry Annotation
This work addresses the problem of fragmented research in Ukiyo-e art analysis for art historians and machine learning researchers, offering an incremental improvement by combining existing methods with new annotations.
The authors tackled the challenge of integrating diverse studies on Ukiyo-e art by proposing a holistic approach, which involved creating a large-scale dataset with semantic and geometric annotations, enabling quantitative object analysis, style study via soft color decomposition, and joint insights through colorization, with the dataset made publicly available.
The study of Ukiyo-e, an important genre of pre-modern Japanese art, focuses on the object and style like other artwork researches. Such study has benefited from the renewed interest by the machine learning community in culturally important topics, leading to interdisciplinary works including collections of images, quantitative approaches, and machine learning-based creativities. They, however, have several drawbacks, and it remains challenging to integrate these works into a comprehensive view. To bridge this gap, we propose a holistic approach We first present a large-scale Ukiyo-e dataset with coherent semantic labels and geometric annotations, then show its value in a quantitative study of Ukiyo-e paintings' object using these labels and annotations. We further demonstrate the machine learning methods could help style study through soft color decomposition of Ukiyo-e, and finally provides joint insights into object and style by composing sketches and colors using colorization. Dataset available at https://github.com/rois-codh/arc-ukiyoe-faces