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.
Authors: Zhewei Huang, Shuchang Zhou, Wen Heng
Institutions: Peking University, Megvii (China)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Keywords: neural rendering, long-term planning
Open Access status: green
OpenAlex ID: W3006025420
