Boundary Matting for View Synthesis
Samuel W. Hasinoff [1], Sing Bing Kang [2], and Richard Szeliski [2]

[1]Dept. of Computer Science
University of Toronto
Toronto, Canada  M5S 3G4
hasinoff@cs.toronto.edu

[2] Interactive Visual Media Group
Microsoft Research
Redmond, WA  98052
{sbkang,szeliski}@microsoft.com

    In the last few years, new view synthesis has emerged as an important
application of 3D stereo reconstruction. While the quality of stereo has
improved, it is still imperfect, and a unique depth is typically assigned to
every pixel. This is problematic at object boundaries, where the boundaries
of objects pixel colors are mixtures of foreground and background colors.
Interpolating views without explicitly accounting for this effect results in
objects with a "cut-out" appearance.
    To produce seamless view interpolation, we propose a method called
boundary matting, which represents each occlusion boundary as a 3D curve. We
show how this method exploits multiple views to perform fully automatic
alpha matting and to simultaneously refine stereo depths at the boundaries.
The key to our approach is the unifying 3D representation of occlusion
boundaries estimated to sub-pixel accuracy. Starting from an initial
estimate derived from stereo, we optimize the curve parameters and the
foreground colors near the boundaries. Our objective function maximizes
consistency with the input images, favors boundaries aligned with strong
edges, and damps large perturbations of the curves. Experimental results
suggest that this method enables high-quality view synthesis with reduced
matting artifacts.

Link
http://www.cs.toronto.edu/~hasinoff/pubs/hasinoff-matting-2004.pdf