Printed texture guided color feature fusion for impressionism style rendering of oil paintings.

Geng, Jing; Ma, Li’e; Li, Xiaoquan; Zhang, Xin; Yan, Yijun

Abstract

As a major branch of Non-Photorealistic Rendering (NPR), image stylization mainly uses computer algorithms to render a photo into an artistic painting. Recent work has shown that the ex-traction of style information such as stroke texture and color of the target style image is the key to image stylization. Given its stroke texture and color characteristics, a new stroke rendering method is proposed. By fully considering the tonal characteristics and the representative color of the original oil painting, it can fit the tone of the original oil painting image into a stylized image whilst keeping the artist's creative effect. The experiments have validated the efficacy of the proposed model in comparison to three state-of-the-arts. This method would be more suitable for the works of pointillism painters with a relatively uniform style, especially for natural scenes, otherwise, the results can be less satisfactory.

Citation

GENG, J., MA, L., LI, X., ZHANG, X. and YAN, Y. 2022. Printed texture guided color feature fusion for impressionism style rendering of oil paintings. Mathematics [online], 10(19): advances in computer vision and machine learning, article 3700. Available from: https://doi.org/10.3390/math10193700

• Journal Article Type: Article
• Acceptance Date: Oct 6, 2022
• Online Publication Date: Oct 9, 2022
• Publication Date: Oct 1, 2022
• Deposit Date: Oct 27, 2022
• Publicly Available Date: Oct 27, 2022
• Journal: Mathematics
• Electronic ISSN: 2227-7390
• Publisher: MDPI
• Peer Reviewed: Peer Reviewed
• Volume: 10
• Issue: 19
• Article Number: 3700
• DOI: https://doi.org/10.3390/math10193700
• Keywords: Image stylization; Feature fusion; Non-photorealistic rendering (NPR)
• Public URL: https://rgu-repository.worktribe.com/output/1791625