1 code implementation • 23 Apr 2021 • Zhengmi Tang, Tomo Miyazaki, Yoshihiro Sugaya, Shinichiro Omachi
To compensate for the lack of pairwise real-world data, we made considerable use of synthetic text after additional enhancement and subsequently trained our model only on the dataset generated by the improved synthetic text engine.
1 code implementation • 24 Aug 2020 • Shoma Iwai, Tomo Miyazaki, Yoshihiro Sugaya, Shinichiro Omachi
To address both of the drawbacks, our method adopts two-stage training and network interpolation.
no code implementations • 16 Apr 2020 • Huy Manh Nguyen, Tomo Miyazaki, Yoshihiro Sugaya, Shinichiro Omachi
A single space is not enough to accommodate various videos and sentences.
no code implementations • 20 Jan 2017 • Tomo Miyazaki, Tatsunori Tsuchiya, Yoshihiro Sugaya, Shinichiro Omachi, Masakazu Iwamura, Seiichi Uchida, Koichi Kise
The proposed method uses strokes from given samples for font generation.