Artist Agent: A Reinforcement Learning Approach to Automatic Stroke Generation in Oriental Ink Painting

2012/06/18 by Ning Xie, Hirotaka Hachiya, Masashi Sugiyama · 1 voice · 9 citations
Computer Science · Engineering · Mathematics · Neuroscience · #3D Shape Modeling and Analysis #Aesthetic Perception and Analysis #Computer Graphics and Visualization Techniques #cs.GR #cs.LG #stat.ML

paper · pdf · doi:10.1587/transinf.e96.d.1134

ICML2012

arxiv created 2012/06/18 · openalex publication_date 2013/01/01 · arxiv updated 2015/06/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Oriental ink painting, called Sumi-e, is one of the most appealing painting styles that has attracted artists around the world. 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 agent, and learn desired brush-trajectories by maximizing the sum of rewards in the policy search framework. We also provide elaborate design of actions, states, and rewards tailored for a Sumi-e agent. The effectiveness of our proposed approach is demonstrated through simulated Sumi-e experiments.

Cited by

• Stylized Neural Painting
• LPaintB: Learning to Paint from Self-Supervision
• Learning to Paint With Model-based Deep Reinforcement Learning
• SketchTransfer: A Challenging New Task for Exploring Detail-Invariance and the Abstractions Learned by Deep Networks
• Differentiable Drawing and Sketching
• Painting Many Pasts: Synthesizing Time Lapse Videos of Paintings
• Conditional Density Estimation with Dimensionality Reduction via Squared-Loss Conditional Entropy Minimization
• Interactive Neural Style Transfer with Artists
• PaintBot: A Reinforcement Learning Approach for Natural Media Painting

Discussions

• Artist Agent: A RL Approach to Stroke Generation in Oriental Ink Painting [hn, 4 points, 0 comments]

Related

• PaintBot: A Reinforcement Learning Approach for Natural Media Painting
• LPaintB: Learning to Paint from Self-Supervision
• Unsupervised Doodling and Painting with Improved SPIRAL
• Intelli-Paint: Towards Developing Human-like Painting Agents
• Learning to Paint With Model-based Deep Reinforcement Learning