LPaintB: Learning to Paint from Self-Supervision

Loading...
Thumbnail Image
Date
2019
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
We present a novel reinforcement learning-based natural media painting algorithm. Our goal is to reproduce a reference image using brush strokes and we encode the objective through observations. Our formulation takes into account that the distribution of the reward in the action space is sparse and training a reinforcement learning algorithm from scratch can be difficult. We present an approach that combines self-supervised learning and reinforcement learning to effectively transfer negative samples into positive ones and change the reward distribution. We demonstrate the benefits of our painting agent to reproduce reference images with brush strokes. The training phase takes about one hour and the runtime algorithm takes about 30 seconds on a GTX1080 GPU reproducing a 1000x800 image with 20,000 strokes.
Description

        
@inproceedings{
10.2312:pg.20191336
, booktitle = {
Pacific Graphics Short Papers
}, editor = {
Lee, Jehee and Theobalt, Christian and Wetzstein, Gordon
}, title = {{
LPaintB: Learning to Paint from Self-Supervision
}}, author = {
Jia, Biao
 and
Brandt, Jonathan
 and
Mech, Radomír
 and
Kim, Byungmoon
 and
Manocha, Dinesh
}, year = {
2019
}, publisher = {
The Eurographics Association
}, ISSN = {
-
}, ISBN = {
978-3-03868-099-4
}, DOI = {
10.2312/pg.20191336
} }
Citation