Name
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. |
Year | Venue | Field |
|---|---|---|
2018 | arXiv: Computer Vision and Pattern Recognition | Computer science,Painting,Supervised learning,Ground truth,Artificial intelligence,Machine learning,Sketch |
DocType | Volume | Citations |
Journal | abs/1810.05977 | 1 |
PageRank | References | Authors |
0.35 | 0 | 8 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Tao Zhou | 1 | 1 | 2.04 |
| Chen Fang | 2 | 1 | 0.35 |
| Zhaowen Wang | 3 | 1063 | 40.64 |
| Jimei Yang | 4 | 1083 | 40.68 |
| B. Kim | 5 | 137 | 17.09 |
| Zhili Chen | 6 | 53 | 4.94 |
| Jonathan Brandt | 7 | 892 | 43.20 |
| Demetri Terzopoulos | 8 | 14080 | 4210.64 |