Non-Photorealistic Computer Graphics Library

[ home · search · about · links · contact · rss ] [ submit bibtex ] [ BookCite · NPR Books ]



Found 7 item(s) authored by "Seungyong Lee" Find Author on Google.

Proceedings Coherent Line Drawing
Henry Kang, Seungyong Lee, Charles K. Chui.
5th International Symposium on Non-Photorealistic Animation (NPAR'07), 2007. [BibTeX]

Article Detail Control in Line Drawings of 3D Meshes
Kyuman Jeong, Alex Ni, Seungyong Lee, Lee Markosian.
The Visual Computer (Pacific Graphics 2005), Vol. 21, No. 8, pp. 698--706, 2005. [BibTeX]

Article Flow-Based Image Abstraction
Henry Kang, Seungyong Lee, Charles K. Chui.
IEEE Transactions on Visualization and Computer Graphics, Vol. 15, No. 1, pp. 62--76, 2009. [BibTeX]

Technical Report Multi-scale Line Drawings from 3D Meshes
Alex Ni, Kyuman Jeong, Seungyong Lee, Lee Markosian.
Department of Electrical Engineering and Computer Science, University of Michigan, No. CSE-TR-510-05, July, 2005. [BibTeX]

Proceedings Multi-scale line drawings from 3D meshes
Alex Ni, Kyuman Jeong, Seungyong Lee, Lee Markosian.
SI3D '06: Proceedings of the 2006 symposium on Interactive 3D graphics and games, pp. 133--137, New York, NY, USA, ACM Press, 2006. [BibTeX]

Proceedings Real-Time Pencil Rendering
Hyunjun Lee, Sungtae Kwon, Seungyong Lee.
NPAR '06: Proceedings of the 4th international symposium on Non-photorealistic animation and rendering, pp. 37--45, New York, NY, USA, ACM Press, 2006. [BibTeX]

Article Shape-simplifying Image Abstraction

Author(s): Henry Kang, Seungyong Lee.
Article: Computer Graphics Forum, Vol. 27, No. 7, pp. 1773--1780, 2008.
[BibTeX] [DOI] Find this paper on Google

This paper presents a simple algorithm for producing stylistic abstraction of a photograph. Based on mean curvature flow in conjunction with shock filter, our method simplifies both shapes and colors simultaneously while preserving important features. In particular, we develop a constrained mean curvature flow, which outperforms the original mean curvature flow in conveying the directionality of features and shape boundaries. The proposed algorithm is iterative and incremental, and therefore the level of abstraction is intuitively controlled. Optionally, simple user masking can be incorporated into the algorithm to selectively control the abstraction speed and to protect particular regions. Experimental results show that our method effectively produces highly abstract yet feature-preserving illustrations from photographs.

Visitors: 150086