Super-Resolution Optical Flow
Existing approaches to super-resolution are not applicable to videos of faces because faces are non-planar, non-rigid, non-lambertian, and are subject to self occlusion. We propose super-resolution optical flow as a solution to these problems. Super-resolution optical flow takes as input a conventional video stream, and simultaneously computes both optical flow and a super-resolution version of the entire video. An example of the algorithm is included below. The input consists of a short video, 5 frames of which are:
The output of our algorithm on those 5 frames is:
A complete video output is:
 |
Displaying 1 Publications
1999
Tech. Report, CMU-RI-TR-99-36, Robotics Institute, Carnegie Mellon University, October, 1999
