Interactive Video Cutout
Michael from Microsoft Research pointed me to a project they’ve been doing with the university of Washington. Key people involved in this research project are: Jue Wang, Pravin Bhat, Alex Colburn, Maneesh Agrawala and Michael Cohen. What they’ve been creating in fact is an interactive system for efficiently extracting foreground objects from a video. They extended previous min-cut based image segmentation techniques to the domain of video with four new contributions.
- A novel painting-based user interface that allows users to easily indicate the foreground object across space and time.
- A hierarchical mean-shift preprocess in order to minimize the number of nodes that min-cut must operate on.
- Within the min-cut they defined a new local cost functions to augment the global costs defined in earlier work.
- Finally, they’ve extended 2D alpha matting methods designed for images to work with 3D video volumes.
v
Video: Interactive Video Cutout
We demonstrate that our matting approach preserves smoothness across both space and time. Our interactive video cutout system allows users to quickly extract foreground objects from video sequences for use in a variety of applications including compositing onto new backgrounds and NPR cartoon style rendering.
Download the paper (58Mb, .pdf)
Download the video (37Mb, DivX)