DeepStyleCam: A Real-Time Style Transfer App on iOS
Ryosuke Tanno Shin Matsuo Wataru Shimoda Keiji Yanai
Department of Informatics, The University of Electro-Communication
In Proc. of International MultiMedia Modeling Conference (MMM 2017)
|
Ryosuke Tanno made the above..
|
Ryosuke Tanno made the above..
|
Abstract
In this demo, we present a very fast CNN-based style transfer system running on normal iPhones. The proposed app can transfer multiple pre-trained styles to the video stream captured from the builtin camera of an iPhone around 140ms (7fps). We extended the network proposed as a real-time neural style transfer network by Johnson et al. [1] so that the network can learn multiple styles at the same time. In addition, we modified the CNN network so that the amount of computation is reduced one tenth compared to the original network. The very fast mobile implementation of the app are based on our paper [2] which describes several new ideas to implement CNN on mobile devices efficiently. Figure 1 shows an example usage of DeepStyleCam which is running on an iPhone SE.
Paper
Citation
Ryosuke Tanno, Shin Matsuo, Wataru Shimoda and Keiji Yanai. "DeepStyleCam: A Real-Time Style Transfer App on iOS", In Proc. of International MultiMedia Modeling Conference (MMM), 2017. Bibtex