EPFL
 Biomedical Imaging GroupSTI
EPFL
  Publications
English only   BIG > Publications > Optical Flow


 CONTENTS
 Home Page
 News & Events
 People
 Publications
 Tutorials and Reviews
 Research
 Demos
 Download Algorithms

 DOWNLOAD
 PDF
 Postscript
 All BibTeX References

A Variational Aggregation Framework for Patch-Based Optical Flow Estimation

D. Fortun, P. Bouthemy, C. Kervrann

Journal of Mathematical Imaging and Vision, vol. 56, no. 2, pp. 280-299, October 2016.



We propose a variational aggregation method for optical flow estimation. It consists of a two-step framework, first estimating a collection of parametric motion models to generate motion candidates, and then reconstructing a global dense motion field. The aggregation step is designed as a motion reconstruction problem from spatially varying sets of motion candidates given by parametric motion models. Our method is designed to capture large displacements in a variational framework without requiring any coarse-to-fine strategy. We handle occlusion with a motion inpainting approach in the candidates computation step. By performing parametric motion estimation, we combine the robustness to noise of local parametric methods with the accuracy yielded by global regularization. We demonstrate the performance of our aggregation approach by comparing it to standard variational methods and a discrete aggregation approach on the Middlebury and MPI Sintel datasets.


@ARTICLE(http://bigwww.epfl.ch/publications/fortun1602.html,
AUTHOR="Fortun, D. and Bouthemy, P. and Kervrann, C.",
TITLE="A Variational Aggregation Framework for Patch-Based Optical Flow
        Estimation",
JOURNAL="Journal of Mathematical Imaging and Vision",
YEAR="2016",
volume="56",
number="2",
pages="280--299",
month="October",
note="")

© 2016 Springer. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from Springer.
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.