Non-Photorealistic Computer Graphics Library

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



Found 7 item(s) authored by "Michael F. Cohen" .

Misc Free-form Video Tooning Deformation
Jue Wang, Ying-Qing Xu, Michael F. Cohen.
Poster on SCA2004, 2004. [BibTeX]

Proceedings Image Precision Silhouette Edges
Ramesh Raskar, Michael F. Cohen.
Symposium on Interactive 3D Graphics (I3D'99), pp. 135--140, Atlanta, Georgia, United States, 1999. [BibTeX]

Proceedings Stylized Video Cubes
Allison W. Klein, Peter-Pike J. Sloan, Adam Finkelstein, Michael F. Cohen.
ACM SIGGRAPH Symposium on Computer Animation, pp. 15--22, July, 2002. [BibTeX]

Proceedings Stylizing 2.5-D Video
Noah Snavely, C. Lawrence Zitnick, Sing Bing Kang, Michael F. Cohen.
NPAR '06: Proceedings of the 4th international symposium on Non-photorealistic animation and rendering, pp. 63--69, New York, NY, USA, June, ACM Press, 2006. [BibTeX]

Article The Cartoon Animation Filter
Jue Wang, Steven Drucker, Maneesh Agrawala, Michael F. Cohen.
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2006), Vol. 23, No. 3, pp. 1169--1173, July, 2006. [BibTeX]

Proceedings Video Mosaics
Allison W. Klein, Tyler Grant, Adam Finkelstein, Michael F. Cohen.
NPAR 2002: Second International Symposium on Non Photorealistic Rendering, pp. 21--28, June, 2002. [BibTeX]

Proceedings Video Tooning

Author(s): Jue Wang, Ying-Qing Xu, Heung-Yeung Shum, Michael F. Cohen.
Proceedings: SIGGAPH2004, 2004.
[BibTeX] Find this paper on Google

We describe a system for transforming an input video into a highly abstracted, spatio-temporally coherent cartoon animation with a range of styles. To achieve this, we treat video as a space-time volume of image data. We have developed an anisotropic kernel mean shift technique to segment the video data into contiguous volumes. These provide a simple cartoon style in themselves, but more importantly provide the capability to semi-automatically rotoscope semantically meaningful regions. In our system, the user simply outlines objects on keyframes. A mean shift guided interpolation algorithm is then employed to create three dimensional semantic regions by interpolation between the keyframes, while maintaining smooth trajectories along the time dimension. These regions provide the basis for creating smooth two dimensional edge sheets and stroke sheets embedded within the spatio-temporal video volume. The regions, edge sheets, and stroke sheets are rendered by slicing them at particular times. A variety of styles of rendering are shown. The temporal coherence provided by the smoothed semantic regions and sheets results in a temporally consistent non-photorealistic appearance.

Visitors: 148561