Learning to Sketch with Deep Q Networks and Demonstrated Strokes
Abstract
Doodling is a useful and common intelligent skill that people can learn and master. In this work, we propose a two-stage learning framework to teach a machine to doodle in a simulated painting environment via Stroke Demonstration and deep Q-learning (SDQ). The developed system, Doodle-SDQ, generates a sequence of pen actions to reproduce a reference drawing and mimics the behavior of human painters. In the first stage, it learns to draw simple strokes by imitating in supervised fashion from a set of strokeaction pairs collected from artist paintings. In the second stage, it is challenged to draw real and more complex doodles without ground truth actions; thus, it is trained with Qlearning. Our experiments confirm that (1) doodling can be learned without direct stepby- step action supervision and (2) pretraining with stroke demonstration via supervised learning is important to improve performance. We further show that Doodle-SDQ is effective at producing plausible drawings in different media types, including sketch and watercolor.
Keywords
Cite
@article{arxiv.1810.05977,
title = {Learning to Sketch with Deep Q Networks and Demonstrated Strokes},
author = {Tao Zhou and Chen Fang and Zhaowen Wang and Jimei Yang and Byungmoon Kim and Zhili Chen and Jonathan Brandt and Demetri Terzopoulos},
journal= {arXiv preprint arXiv:1810.05977},
year = {2018}
}