Meet Inspiring Speakers and Experts at our 3000+ Global Conference Series Events with over 1000+ Conferences, 1000+ Symposiums
and 1000+ Workshops on Medical, Pharma, Engineering, Science, Technology and Business.

Explore and learn more about Conference Series : World's leading Event Organizer

Back

Tien-Tsin Wong

Tien-Tsin Wong

Chinese University of Hong Kong, Hong Kong

Title: Computational Manga and Anime

Biography

Biography: Tien-Tsin Wong

Abstract

Traditional manga (comic) and anime (cartoon) creation are painstaking processes. Even computers are utilized during the production, they are mainly utilized as a naive digital canvas. With the increasing computing power and decreasing cost of CPU & GPU, more computing resource can be exploited cost-effectively for intelligent and semi-automatic creation of aesthetics content. In this talk, we present our recent works on computational manga and anime, in which we aim at facilitating various production steps with the advanced computer technologies. Manga artists usually draw the backgrounds based on real photographs. Such background preparation is tedious and time-consuming. Some artists already make use of simple computer techniques, such as halftoning, to convert a given color photograph into B/W manga. However, the resultant mangas are so inconsistent in style and monotonous in pattern due to the single halftone screen. I will present a way to turn a color photograph into manga while preserving the color distinguishability in the original photo, just like what traditional manga artists do. On the other hand, there is a trend of migrating manga publishing from the traditional paper medium to the digital domain via the screen of portable devices. There are companies doing colorization for B/W mangas (of course, in a painstaking manual fashion) to allow users to read color manga on the portable devices. I will present a computer-assisted method to colorize an originally B/W manga into a color version by simply scribbling on the B/W version. Lastly, I will present our latest work on automatically conversion of 2D hand-drawn cel animations to stereoscopic ones. As it is infeasible to ask cel animators to draw stereo-frames, there is a rare number of stereo cel animation produced so far. I will present a method to exploit the scarce amount of depth cue left in the hand-drawn animation, in order to synthesize the temporal-consistent and visually plausible stereoscopic cel animation.