A researcher from Fudan University gave a talk on creating anime characters with artificial intelligence.
Nijigenka (二次元化) in Japanese or “2D-ification” describes a process of artists turning photos of people into anime characters. It’s time to forget about the traditional approach. You can now use AI for an image-to-image translation! A researcher from Fudan University gave a talk on creating anime characters with artificial intelligence at a recent workshop about deep learning in Tokyo. Researchers have found a way to use deep learning to generate anime versions of real photos.
Watch the video below to study the team’s results:
The workshop aims at bringing together leading scientists in deep learning and related areas within machine learning, artificial intelligence, mathematics, statistics, and neuroscience. No formal submission is required. Speakers are invited to present their recently published work as well as work in progress, and to share their vision and perspectives for the field.
The process is not that easy as anime presents certain standards for characters. The team faced some challenges, so they had to tune their method. Their results are still not perfect, but we expect great things from the team.