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

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.

ICML2012

Cited by in corpus (20)

• Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges
• Learning to Paint With Model-based Deep Reinforcement Learning
• Neural Painters: A learned differentiable constraint for generating brushstroke paintings
• Learning to Sketch with Deep Q Networks and Demonstrated Strokes
• Computational Approaches for Traditional Chinese Painting: From the "Six Principles of Painting" Perspective
• Im2Oil: Stroke-Based Oil Painting Rendering with Linearly Controllable Fineness Via Adaptive Sampling
• Freehand Sketch Generation from Mechanical Components
• Unsupervised Image to Sequence Translation with Canvas-Drawer Networks
• Differentiable Drawing and Sketching
• Modeling 3D Shapes by Reinforcement Learning
• Interactive Neural Painting
• PaintBot: A Reinforcement Learning Approach for Natural Media Painting
• LPaintB: Learning to Paint from Self-Supervision
• Stroke-based Character Reconstruction
• Interactive Neural Style Transfer with Artists
• Painting Many Pasts: Synthesizing Time Lapse Videos of Paintings
• Combining Semantic Guidance and Deep Reinforcement Learning For Generating Human Level Paintings
• Stylized Neural Painting
• SketchTransfer: A Challenging New Task for Exploring Detail-Invariance and the Abstractions Learned by Deep Networks
• Conditional Density Estimation with Dimensionality Reduction via Squared-Loss Conditional Entropy Minimization