Existing video matting approaches determine the alpha matte sequence frame-by-frame, which lead to flickering near the boundary of the foreground region. We reduce this effect by considering video data as a spatio-temporal cube, and extending a robust matting algorithm to a 3D solver. Our results demonstrate consistent and visually pleasing alpha mattes, and tend to preserve temporal coherence better than previous techniques. Crown
Bibliographical noteFunding Information:
This work was supported by the IT R&D program of MKE/MCST/IITA ( 2008-F-031-01 , Development of Computational Photography Technologies for Image and Video Contents).
All Science Journal Classification (ASJC) codes
- Modelling and Simulation
- Geometry and Topology
- Computer Graphics and Computer-Aided Design