Work

Learning to Paint With Model-Based Deep Reinforcement Learning

Year: 2019
Type: conference-paper
Abstract: 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.
Language: English
Open Access status: green
OpenAlex ID: W3006025420
FWCI: 6.386
Cites: 50
Cited by: 215
Related to: 9