Computer Graphics
TU Braunschweig

Spectral Video Matting

Spectral Video Matting

We present a new, simple-to-use and rapid approach to video matting, the process of pulling a high-quality alpha matte from a video sequence.

Our approach builds upon techniques in natural image matting, namely spectral matting, and optical flow computation.

No additional hardware, despite a single camera, is needed, and only very few and intuitive user interactions are required for foreground estimation.

For certain scenes the approach is able to estimate the alpha matte for a video, consisting of up to 102 frames, without any user interaction at all.

Author(s):Martin Eisemann, Julia Wolf, Marcus Magnor
Published:November 2009
Type:Article in conference proceedings
Book:Proc. Vision, Modeling and Visualization (VMV)
Presented at:Vision, Modeling and Visualization (VMV) 2009

  title = {Spectral Video Matting},
  author = {Eisemann, Martin and Wolf, Julia and Magnor, Marcus},
  booktitle = {Proc. Vision, Modeling and Visualization ({VMV})},
  organization = {Eurographics},
  pages = {121--126},
  month = {Nov},
  year = {2009}