Stylizing 2½-D Video

Noah Snavely1     C. Lawrence Zitnick2     Sing Bing Kang2     Michael F. Cohen2    
1University of Washington     2Microsoft Research


In recent years considerable interest has been given to non-photorealistic rendering of photographs, video, and 3D models for illustrative or artistic purposes. Conventional 2D inputs such as photographs and video are easy to create and capture, while 3D models allow for a wider variety of stylization techniques, such as cross-hatching. In this paper, we propose using video with depth information (\2.5D video) to combine the advantages of 2D and 3D input. 2.5D video is becoming increasingly easy to capture, and with the additional depth information, stylization techniques that require shape information can be applied. However, because 2.5D video contains only limited shape information and 3D correspondence over time is unknown, it is difficult to create temporally coherent stylized animations directly from raw 2.5D video. In this paper, we present techniques for processing 2.5D video to overcome these drawbacks, and demonstrate several styles that can be created using these techniques.


Noah Snavely, C. Lawrence Zitnick, Sing Bing Kang, Michael F. Cohen. Stylizing 2.5-D Video. Proceedings of the Symposium on Non-Photorealistic Animation and Rendering, 2006. [pdf] [bibtex]


[~40 MB .MOV file]