Article

Consistent Segmentation for Optical Flow Estimation

Authors:

C. Lawrence Zitnick,

Nebojsa Jojic,

Sing Bing KangAuthors Info & Claims

ICCV '05: Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2

Pages 1308 - 1315

https://doi.org/10.1109/ICCV.2005.61

Published: 17 October 2005 Publication History

Publisher Site

Abstract

In this paper, we propose a method for jointly computing optical flow and segmentating 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 (á) 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.

Cited By

View all

Tang HTao PMa RShi Y(2019)Video Object Segmentation with 3D Convolution NetworkProceedings of the 2nd International Conference on Control and Computer Vision10.1145/3341016.3341031(28-32)Online publication date: 15-Jun-2019
https://dl.acm.org/doi/10.1145/3341016.3341031
Lobachev OSteiniger BGuthe MZemcik PBittner JViola I(2017)Compensating anisotropy in histological serial sections with optical flow-based interpolationProceedings of the 33rd Spring Conference on Computer Graphics10.1145/3154353.3154366(1-11)Online publication date: 15-May-2017
https://dl.acm.org/doi/10.1145/3154353.3154366
Bista SCunha ÍVarshney A(2017)Kinetic depth imagesThe Visual Computer: International Journal of Computer Graphics10.1007/s00371-016-1231-233:10(1357-1369)Online publication date: 1-Oct-2017
https://dl.acm.org/doi/10.1007/s00371-016-1231-2
Show More Cited By

Index Terms

Consistent Segmentation for Optical Flow Estimation
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
  2. Computer graphics
    1. Animation
      1. Motion capture
      2. Motion processing

Recommendations

Joint optical flow estimation, segmentation, and 3D interpretation with level sets

This paper describes a variational method with active curve evolution and level sets for the estimation, segmentation, and 3D interpretation of optical flow generated by independently moving rigid objects in space. Estimation, segmentation, and 3D ...
3D motion segmentation from straight-line optical flow
MCAM'07: Proceedings of the 2007 international conference on Multimedia content analysis and mining

We present a closed form solution to the problem of segmenting multiple 3D motion models from straight-line optical flow. We introduce the multibody line optical flow constraint(MLOFC), a polynomial equation relating motion models and line parameters. ...
Optical flow estimation for motion-compensated compression

The computation of optical flow within an image sequence is one of the most widely used techniques in computer vision. In this paper, we present a new approach to estimate the velocity field for motion-compensated compression. It is derived by a ...

Comments

Information & Contributors

Information

Published In

ICCV '05: Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2

October 2005

941 pages

ISBN:076952334X02

Publisher

IEEE Computer Society

United States

Publication History

Published: 17 October 2005

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

22
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 27 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

View all

Tang HTao PMa RShi Y(2019)Video Object Segmentation with 3D Convolution NetworkProceedings of the 2nd International Conference on Control and Computer Vision10.1145/3341016.3341031(28-32)Online publication date: 15-Jun-2019
https://dl.acm.org/doi/10.1145/3341016.3341031
Lobachev OSteiniger BGuthe MZemcik PBittner JViola I(2017)Compensating anisotropy in histological serial sections with optical flow-based interpolationProceedings of the 33rd Spring Conference on Computer Graphics10.1145/3154353.3154366(1-11)Online publication date: 15-May-2017
https://dl.acm.org/doi/10.1145/3154353.3154366
Bista SCunha ÍVarshney A(2017)Kinetic depth imagesThe Visual Computer: International Journal of Computer Graphics10.1007/s00371-016-1231-233:10(1357-1369)Online publication date: 1-Oct-2017
https://dl.acm.org/doi/10.1007/s00371-016-1231-2
Buyssens PGardin IRuan SElmoataz A(2014)Eikonal-based region growing for efficient clusteringImage and Vision Computing10.1016/j.imavis.2014.10.00232:12(1045-1054)Online publication date: 1-Dec-2014
https://dl.acm.org/doi/10.1016/j.imavis.2014.10.002
Chaurasia GDuchene SSorkine-Hornung ODrettakis G(2013)Depth synthesis and local warps for plausible image-based navigationACM Transactions on Graphics10.1145/2487228.248723832:3(1-12)Online publication date: 4-Jul-2013
https://dl.acm.org/doi/10.1145/2487228.2487238
Al Harbi NGotoh Y(2013)Spatio-temporal Human Body Segmentation from Video StreamProceedings, Part I, of the 15th International Conference on Computer Analysis of Images and Patterns - Volume 804710.1007/978-3-642-40261-6_9(78-85)Online publication date: 27-Aug-2013
https://dl.acm.org/doi/10.1007/978-3-642-40261-6_9
Heinrich MJenkinson MPapież BGlesson FBrady SSchnabel J(2013)Edge- and detail-preserving sparse image representations for deformable registration of chest MRI and CT volumesProceedings of the 23rd international conference on Information Processing in Medical Imaging10.1007/978-3-642-38868-2_39(463-474)Online publication date: 28-Jun-2013
https://dl.acm.org/doi/10.1007/978-3-642-38868-2_39
Van den Bergh MBoix XRoig Gde Capitani BVan Gool L(2012)SEEDSProceedings of the 12th European conference on Computer Vision - Volume Part VII10.1007/978-3-642-33786-4_2(13-26)Online publication date: 7-Oct-2012
https://dl.acm.org/doi/10.1007/978-3-642-33786-4_2
Stich TLinz CWallraven CCunningham DMagnor M(2011)Perception-motivated interpolation of image sequencesACM Transactions on Applied Perception10.1145/1870076.18700798:2(1-25)Online publication date: 2-Feb-2011
https://dl.acm.org/doi/10.1145/1870076.1870079
Héas PHerzet CMémin E(2011)Robust optic-flow estimation with bayesian inference of model and hyper-parametersProceedings of the Third international conference on Scale Space and Variational Methods in Computer Vision10.1007/978-3-642-24785-9_65(773-785)Online publication date: 29-May-2011
https://dl.acm.org/doi/10.1007/978-3-642-24785-9_65
Show More Cited By

Abstract

Cited By

Index Terms

Recommendations

Joint optical flow estimation, segmentation, and 3D interpretation with level sets

3D motion segmentation from straight-line optical flow

Optical flow estimation for motion-compensated compression

Comments

Information

Published In

Publisher

Publication History

Qualifiers

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

View options

Share

Share this Publication link

Share on social media

Affiliations