The artistic style transfer from Shanghai modern landmark buildings images to Xiao Jiaochang New Year pictures based on deep learning

Abstract

Posting New Year pictures is a folk custom with a long history in China. Shanghai New Year pictures are loved by the people with its unique Shanghai style. As a representative of Shanghai New Year pictures, Xiao Jiaochang New Year pictures have left a strong mark in the history of Shanghai style culture and history through its diverse and comprehensive categories and rich artistic styles. However, due to its short well-developed period, the New Year pictures in Xiao Jiaochang have no inheritance and cannot apply for intangible cultural heritage. Nowadays, it is not realistic for us to use the traditional way to make New Year pictures in small schools because of the lack of inheritors and the production techniques have not been continued. Therefore, this paper mainly focuses on tracing back to this period of history, and realize the recording and dissemination of the style of the New Year pictures of Xiao Jiaochang through modern high-tech. Collect the relatively complete New Year pictures of Xiao Jiaochang in the world as a data set, and realize the style transfer to modern Shanghai's landmark buildings' pictures through the method of machine learning. Realizing the electronic work on spreading the culture in addition to the normal electronic record needs to be in time, so that Xiao Jiaochang New Year pictures can reappear in the world.