An example-based approach to style translation for line drawings

We present an example-based system for translating line drawings into different styles. The system is given a training set of many different lines, each drawn by an artist in various styles, which is used to translate new lines made by a user into a particular desired style with a it K-nearest neighbor algorithm. This algorithm fits each input line as a linear combination of the several training lines in the same style which are most similar to it. The fit line can then be rendered in different styles because the training set contains versions of each training line in each style. Our example-based approach has a number of advantages over conventional parameteric approaches to translating style. It can handle styles which are difficult to describe parametrically, and its repertoire can be easily extended by the user at any time. Moreover, given appropriate representations, it can be generalized to modify the style of other kinds of graphics objects, such as the font of a letter or the movement style of an animated character. This work may not be copied or reproduced in whole or in part for any commercial purpose. Permission to copy in whole or in part without payment of fee is granted for nonprofit educational and research purposes provided that all such whole or partial copies include the following: a notice that such copying is by permission of Mitsubishi Electric Research Laboratories, Inc.; an acknowledgment of the authors and individual contributions to the work; and all applicable portions of the copyright notice. Copying, reproduction, or republishing for any other purpose shall require a license with payment of fee to Mitsubishi Electric Research Laboratories, Inc. All rights reserved. Copyright c ©Mitsubishi Electric Research Laboratories, Inc., 1999 201 Broadway, Cambridge, Massachusetts 02139