Open Access

ARTICLE

Stroke Based Painterly Rendering with Mass Data through Auto Warping Generation

Taemin Lee¹, Beomsik Kim², Sanghyun Seo³, Kyunghyun Yoon^4,*

1 Davinci SW Education Institute, Chung-Ang University, Seoul, 06974, South Korea
2 School of Computer Science and Engineering, Chung-Ang University, Seoul, 06974, South Korea
3 College of Art & Technology, Chung-Ang University, Gyeonggi-do, 17546, South Korea
4 School of Computer Science and Engineering, Chung-Ang University, Seoul, 06974, South Korea

* Corresponding Author: Kyunghyun Yoon. Email:

(This article belongs to the Special Issue: HPC with Artificial Intelligence based Deep Video Data Analytics: Models, Applications and Approaches)

Computer Modeling in Engineering & Sciences 2022, 130(3), 1441-1457. https://doi.org/10.32604/cmes.2022.018010

Received 23 June 2021; Accepted 13 September 2021; Issue published 30 December 2021

Abstract

Painting is done according to the artist's style. The most representative of the style is the texture and shape of the brush stroke. Computer simulations allow the artist's painting to be produced by taking this stroke and pasting it onto the image. This is called stroke-based rendering. The quality of the result depends on the number or quality of this stroke, since the stroke is taken to create the image. It is not easy to render using a large amount of information, as there is a limit to having a stroke scanned. In this work, we intend to produce rendering results using mass data that produces large amounts of strokes by expanding existing strokes through warping. Through this, we have produced results that have higher quality than conventional studies. Finally, we also compare the correlation between the amount of data and the results.

---

Keywords

---