In this paper, we propose a method for jointly computing optical flow and segmenting video while accounting for mixed pixels (matting). Our method is based on statistical modeling of an image pair using constraints on appearance and motion. Segments are viewed as overlapping regions with fractional (/spl alpha/) contributions. Bidirectional motion is estimated based on spatial coherence and similarity of segment colors. Our model is extended to video by chaining the pairwise models to produce a joint probability distribution to be maximized. To make the problem more tractable, we factorize the posterior distribution and iteratively minimize its parts. We demonstrate our method on frame interpolation.
Consistent segmentation for optical flow estimation
Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 ; 2 ; 1308-1315 Vol. 2
2005-01-01
847379 byte
Conference paper
Electronic Resource
English
Consistent Segmentation for Optical Flow Estimation
British Library Conference Proceedings | 2005
|Consistent link flow estimation from counts
Elsevier | 1981
|Spatially consistent 3D motion segmentation
IEEE | 2005
|Spatially Consistent 3D Motion Segmentation
British Library Conference Proceedings | 2005
|