A generative model of dense optical flow in layers

Authors:
Anitha Kannan;Brendan Frey;Nebojsa Jojic
Affiliations:
Probabilistic and Statistical Inference Group, University of Toronto, Canada;Probabilistic and Statistical Inference Group, University of Toronto, Canada;Microsoft Research, Redmond
Venue:
SCVMA'04 Proceedings of the First international conference on Spatial Coherence for Visual Motion Analysis
Year:
2004

Citing 6
Cited 0

Performance of optical flow techniques

International Journal of Computer Vision
A Unified Mixture Framework for Motion Segmentation: Incorporating Spatial Coherence and Estimating the Number of Models

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Layered representation of motion video using robust maximum-likelihood estimation of mixture models and MDL encoding

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
A Background Layer Model for Object Tracking Through Occlusion

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
An iterative image registration technique with an application to stereo vision

IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
Video-rate stereo depth measurement on programmable hardware

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

We introduce a generative model of dense flow fields within a layered representation of 3-dimensional scenes. Using probabilistic inference and learning techniques (namely, variational methods), we solve the inverse problem and locally segment the foreground from the background, estimate the nonuniform motion of each, and fill in the disocclusions. To illustrate the usefulness of both the representation and the estimation algorithm, we show results on stabilization and frame interpolation that are obtained by generating from the trained models.