AI Turns People Into Anime Characters
Events
Subscribe:  iCal  |  Google Calendar
Cologne DE   18, Aug — 20, Aug
Cologne DE   20, Aug — 25, Aug
Vienna AT   23, Aug — 25, Aug
Anaheim US   27, Aug — 30, Aug
SEATTLE US   30, Aug — 3, Sep
Latest comments
by jeewangarg
25 min ago

Jeewangarg provides Best SEO Services in Delhi. We offer Best SEO services to improve your online presence. Visit us - https://www.jeewangarg.com/seo-services-delhi-india.html

by Air Purifier
2 hours ago

BreathFresh is redefining the way you live with the all new Natural Air Purifier. Make your home or offices breathable and say yes to a healthier life. Buy affordable and Best Air Purifier in India. by browsing us online on: https://breathefresh.in

by Air Purifier
2 hours ago

Thanks for sharing such great information and here we are India’s best service provider of Natural Air Purifier. Make your home or offices breathable and say yes to a healthier life. Buy affordable and Best Air Purifier in India.

AI Turns People Into Anime Characters
7 June, 2018
News

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. 

You can find the full paper with a thorough breakdown here
Source: arxiv.org

Leave a Reply

avatar