Born in 1929 in Osaka, Japan, Osamu Tezuka is known in Japan and around the world as the Father of Manga. He's also known as one of the world's greatest illustrators, akin to Walt Disney, from his legendary comics that include Astro Boy, Princess Knight, Kimba the White Lion, and many more. Tezuka died in 1989. To keep his legacy alive, a team of researchers, and artists from Kioxia Coporation, a Japanese memory manufacturer, in collaboration with artist from Tezuka Production and academic partners, used deep learning to create the world's first AI-designed manga, reflecting Tezuka's works. The new manga, PHAEDO, is released in the weekly comic magazine, Morning. To generate the new characters and stories featured in the manga, the team used Nvidia StyleGan to help with the character generation phase by analyzing hundred of works by Tezuka, including Phoeniix, Black Jack, and Astro Boy. The God of Manga, Osamu Tezuka, taught us the joy of depicting dreams through technology. At the same time, he insisted that science should not leave humanity behind. In 2020, we now live in a world that Osamu Tezuka imagined.
The company worked in tandem with academic partners, including Satoshi Kurihara, professor at Keio University. "In order to have AI learn the characteristics of Osamu Tezuka, we used manpower and AI that specializes in image recognition to convert the parts of characters' faces into data and analyze the development of various scenarios. With AI learning the characteristics of Osamu Tezuka through this data, we generated characters and storylines that have Tezuka's characteristics," Kurihara stated. At the core of the character generation phase is NVIDIA's StyleGan a generative adversarial netwrok developed by NVIDIA researchers. To build a training dataset to use with StyleGan, Professor Kazushi Mukaiyama from Future Univeristy Hakodate enlisted students' help. Together, they compiled a dataset of over 10,000 facial images from Tezuka's work that could be used to train the model. 150,000 pages of manuscipt data from Osamu Tezuka were prepared for the AI to learn what "Tezuka-like" characters are. These were passed through the recognition software at Future University Hakodate, and were classified as "frames," "speech balloons," "faces," and "bodies." To improve the quality of the images generated by AI, the staff repeated a process of trial and error until the ideal images were generated. For example: flipping, doubling the number of images, loading only female characters, and so on.
Training and inference were done using multiple NVIDIA V100 GPUs, and the cuDNN accelerated TensorFlow deep learning framework which StyleGan is written in. In the first phase, StyleGAN generated the faces in a single process. "For this reason, the team attempted to generate more complete images, in which fine details like the eyes, nose, and mouth are gradually generated from rough depictions, such as contours," the researchers said. Ultimately, the team used transfer learning to incorporate thousands of data points to enable the Tezuka-like characters without fail. "By combining different individual features of the characters, we found that characters with unprecedented characteristics could be created. This mechanism relies on creating a number of variations by gradually changing the ratio of the two characters that are mixed," the researched showed. Toshihiro Miura, the Editor-in-Chief of Morning, the publication in which the final product appears, said that he first declined the project after learning how much human intervention was involved. He said that he changed his mind later after talking to professor Kurihara and seeing that the work reaffirms the work of human artists and how 'incredible' they are. SOURCE:news.developer.nvidia.com/osamu-tezuka-ai-supporterd-manga/
No lines are longer than 80 characters, TYVM.
Other specified properties aren’t being scored automatically at this time so this is not necessarily good news…