Learning to Paint With Model-based Deep Reinforcement Learning
This addresses the challenge of automated artistic rendering for applications in digital art and graphics, though it is incremental as it builds on existing model-based deep reinforcement learning methods.
The paper tackles the problem of teaching machines to create paintings using a small number of strokes, achieving excellent visual effects with hundreds of strokes without requiring human painter experience or stroke tracking data.
We show how to teach machines to paint like human painters, who can use a small number of strokes to create fantastic paintings. By employing a neural renderer in model-based Deep Reinforcement Learning (DRL), our agents learn to determine the position and color of each stroke and make long-term plans to decompose texture-rich images into strokes. Experiments demonstrate that excellent visual effects can be achieved using hundreds of strokes. The training process does not require the experience of human painters or stroke tracking data. The code is available at https://github.com/hzwer/ICCV2019-LearningToPaint.