Keyframe-Based Tracking for Rotoscoping and Animation
Aseem Agarwala1
Aaron Hertzmann2
David H. Salesin1,3
Steven M. Seitz1
1University of Washington
2University of Toronto
3Microsoft Research
Abstract
We describe a new approach to rotoscoping --- the process of tracking
contours in a video sequence --- that combines computer vision with
user interaction. In order to track contours in video, the user
specifies curves in two or more frames; these curves are used as
keyframes by a computer-vision-based tracking algorithm. The user may
interactively refine the curves and then restart the tracking
algorithm. Combining computer vision with user interaction allows our
system to track any sequence with significantly less effort than
interpolation-based systems --- and with better reliability than
"pure" computer vision systems. Our tracking algorithm is cast as a
spacetime optimization problem that solves for time-varying curve
shapes based on an input video sequence and user-specified
constraints. We demonstrate our system with several rotoscoped
examples. Additionally, we show how these rotoscoped contours can be
used to help create cartoon animation by attaching user-drawn strokes
to the tracked contours.
Citation
Aseem Agarwala, Aaron Hertzmann, David Salesin, Steven Seitz.
Keyframe-Based Tracking for Rotoscoping and Animation.
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2004), 2004.
Paper
SIGGRAPH 2004 pre-print (2.4MB PDF)
Video
Bigger video (720x480, 122 MB, MPEG4 AVI)
Smaller video (360x240, 40 MB, MPEG4 AVI)
Source code
The source code for this project is available here.
