IEICE TRANSACTIONS on Information
Artist Agent: A Reinforcement Learning Approach to Automatic Stroke Generation in Oriental Ink Painting
Summary :
Oriental ink painting, called Sumi-e, is one of the most distinctive painting styles and has attracted artists around the world. Major challenges in Sumi-e simulation are to abstract complex scene information and reproduce smooth and natural brush strokes. To automatically generate such strokes, we propose to model the brush as a reinforcement learning agent, and let the agent learn the desired brush-trajectories by maximizing the sum of rewards in the policy search framework. To achieve better performance, we provide elaborate design of actions, states, and rewards specifically tailored for a Sumi-e agent. The effectiveness of our proposed approach is demonstrated through experiments on Sumi-e simulation.
- Publication
- IEICE TRANSACTIONS on Information Vol.E96-D No.5 pp.1134-1144
- Publication Date
- 2013/05/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E96.D.1134
- Type of Manuscript
- PAPER
- Category
- Artificial Intelligence, Data Mining
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Ning XIE, Hirotaka HACHIYA, Masashi SUGIYAMA, "Artist Agent: A Reinforcement Learning Approach to Automatic Stroke Generation in Oriental Ink Painting" in IEICE TRANSACTIONS on Information,
vol. E96-D, no. 5, pp. 1134-1144, May 2013, doi: 10.1587/transinf.E96.D.1134.
Abstract: Oriental ink painting, called Sumi-e, is one of the most distinctive painting styles and has attracted artists around the world. Major challenges in Sumi-e simulation are to abstract complex scene information and reproduce smooth and natural brush strokes. To automatically generate such strokes, we propose to model the brush as a reinforcement learning agent, and let the agent learn the desired brush-trajectories by maximizing the sum of rewards in the policy search framework. To achieve better performance, we provide elaborate design of actions, states, and rewards specifically tailored for a Sumi-e agent. The effectiveness of our proposed approach is demonstrated through experiments on Sumi-e simulation.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E96.D.1134/_p
Copy
@ARTICLE{e96-d_5_1134,
author={Ning XIE, Hirotaka HACHIYA, Masashi SUGIYAMA, },
journal={IEICE TRANSACTIONS on Information},
title={Artist Agent: A Reinforcement Learning Approach to Automatic Stroke Generation in Oriental Ink Painting},
year={2013},
volume={E96-D},
number={5},
pages={1134-1144},
abstract={Oriental ink painting, called Sumi-e, is one of the most distinctive painting styles and has attracted artists around the world. Major challenges in Sumi-e simulation are to abstract complex scene information and reproduce smooth and natural brush strokes. To automatically generate such strokes, we propose to model the brush as a reinforcement learning agent, and let the agent learn the desired brush-trajectories by maximizing the sum of rewards in the policy search framework. To achieve better performance, we provide elaborate design of actions, states, and rewards specifically tailored for a Sumi-e agent. The effectiveness of our proposed approach is demonstrated through experiments on Sumi-e simulation.},
keywords={},
doi={10.1587/transinf.E96.D.1134},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Artist Agent: A Reinforcement Learning Approach to Automatic Stroke Generation in Oriental Ink Painting
T2 - IEICE TRANSACTIONS on Information
SP - 1134
EP - 1144
AU - Ning XIE
AU - Hirotaka HACHIYA
AU - Masashi SUGIYAMA
PY - 2013
DO - 10.1587/transinf.E96.D.1134
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2013
AB - Oriental ink painting, called Sumi-e, is one of the most distinctive painting styles and has attracted artists around the world. Major challenges in Sumi-e simulation are to abstract complex scene information and reproduce smooth and natural brush strokes. To automatically generate such strokes, we propose to model the brush as a reinforcement learning agent, and let the agent learn the desired brush-trajectories by maximizing the sum of rewards in the policy search framework. To achieve better performance, we provide elaborate design of actions, states, and rewards specifically tailored for a Sumi-e agent. The effectiveness of our proposed approach is demonstrated through experiments on Sumi-e simulation.
ER -
English
