Stroke-based stylization learning and rendering with inverse reinforcement learning

Authors: Xie, N., Zhao, T., Tian, F., Zhang, X.H. and Sugiyam, M.

http://eprints.bournemouth.ac.uk/22693/

Start date: 25 July 2015

This data was imported from Scopus:

Authors: Xie, N., Zhao, T., Tian, F., Zhang, X. and Sugiyama, M.

http://eprints.bournemouth.ac.uk/22693/

Journal: IJCAI International Joint Conference on Artificial Intelligence

Volume: 2015-January

Pages: 2531-2539

ISBN: 9781577357384

ISSN: 1045-0823

Among various traditional art forms, brush stroke drawing is one of the widely used styles in modern computer graphic tools such as GIMP, Photoshop and Painter. In this paper, we develop an AI-aided art authoring (A4) system of non-photorealistic rendering that allows users to automatically generate brush stroke paintings in a specific artist's style. Within the reinforcement learning framework of brush stroke generation proposed by Xie et al. [Xie et al., 2012], our contribution in this paper is to learn artists' drawing styles from video-captured stroke data by inverse reinforcement learning. Through experiments, we demonstrate that our system can successfully learn artists' styles and render pictures with consistent and smooth brush strokes.

This data was imported from Web of Science (Lite):

Authors: Xie, N., Zhao, T., Tian, F., Zhang, X. and Sugiyama, M.

http://eprints.bournemouth.ac.uk/22693/

Journal: PROCEEDINGS OF THE TWENTY-FOURTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI)

Pages: 2531-2537

The data on this page was last updated at 05:18 on July 20, 2019.