Consistent segmentation for optical flow estimation
- 1 January 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3 (15505499), 1308-1315
- https://doi.org/10.1109/iccv.2005.61
Abstract
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 (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 interpolationKeywords
This publication has 19 references indexed in Scilit:
- Object based segmentation of video using color, motion and spatial informationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- High-quality video view interpolation using a layered representationPublished by Association for Computing Machinery (ACM) ,2004
- Video tooningACM Transactions on Graphics, 2004
- Smoothness in layers: Motion segmentation using nonparametric mixture estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A global matching framework for stereo computationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Factor graphs and the sum-product algorithmIEEE Transactions on Information Theory, 2001
- Region-based video coder using edge flow segmentation and hierarchical affine region matchingPublished by SPIE-Intl Soc Optical Eng ,1998
- A View of the Em Algorithm that Justifies Incremental, Sparse, and other VariantsPublished by Springer Nature ,1998
- Spline-Based Image RegistrationInternational Journal of Computer Vision, 1997
- Representing moving images with layersIEEE Transactions on Image Processing, 1994