Artist Agent A2: Stroke Painterly Rendering Based on Reinforcement Learning

• Item type: SIG Technical Reports(1)
• 公開日: 2011-08-29
• タイトル: Artist Agent A2: Stroke Painterly Rendering Based on Reinforcement Learning
• タイトル / 言語: en
• タイトル: Artist Agent A2: Stroke Painterly Rendering Based on Reinforcement Learning
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: テーマセッション4
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Department of Computer Science, Tokyo Institute of Technology
• 著者所属: Department of Computer Science, Tokyo Institute of Technology
• 著者所属: Department of Computer Science, Tokyo Institute of Technology
• 著者所属(英): en
• 著者所属(英): Department of Computer Science, Tokyo Institute of Technology
• 著者所属(英): en
• 著者所属(英): Department of Computer Science, Tokyo Institute of Technology
• 著者所属(英): en
• 著者所属(英): Department of Computer Science, Tokyo Institute of Technology
• 著者名: Ning, Xie; Hirotaka, Hachiya; Masashi, Sugiyama
• 著者名(英): Ning, Xie; Hirotaka, Hachiya; Masashi, Sugiyama
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Oriental ink painting, called Sumi-e, is one of the most appealing painting styles that has attracted artists around the world. The major challenges in computer-based Sumi-e simulation are to abstract complex scene information and draw smooth and natural brush strokes. To automatically find such strokes, we propose to model the brush as a reinforcement-learning (RL) agent, and learn desired brush-trajectories by maximizing the sum of rewards in the policy search framework. We also provide elaborate design of state space, action space, and a reward function tailored for a Sumi-e agent. The effectiveness of our proposed approach is demonstrated through simulated Sumi-e experiments.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Oriental ink painting, called Sumi-e, is one of the most appealing painting styles that has attracted artists around the world. The major challenges in computer-based Sumi-e simulation are to abstract complex scene information and draw smooth and natural brush strokes. To automatically find such strokes, we propose to model the brush as a reinforcement-learning (RL) agent, and learn desired brush-trajectories by maximizing the sum of rewards in the policy search framework. We also provide elaborate design of state space, action space, and a reward function tailored for a Sumi-e agent. The effectiveness of our proposed approach is demonstrated through simulated Sumi-e experiments.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA11131797
• 書誌情報: 研究報告コンピュータビジョンとイメージメディア（CVIM）; 巻 2011-CVIM-178, 号 18, p. 1-7, 発行日 2011-08-29
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会