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

TL;DR

This paper introduces a reinforcement learning-based method for automatic stroke generation in Oriental ink painting, specifically Sumi-e, by modeling the brush as an agent to produce natural brush strokes.

Contribution

It presents a novel reinforcement learning framework tailored for Sumi-e, including custom actions, states, and rewards for realistic stroke synthesis.

Findings

Effective automatic stroke generation demonstrated in simulated experiments

Reinforcement learning successfully models brush trajectories for natural appearance

Framework can potentially be extended to other artistic styles

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.