Large displacement optical flow computation without warping

Frank Steinbrücker, Thomas Pock, Daniel Cremers

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

129 Scopus citations

Abstract

We propose an algorithm for large displacement optical flow estimation which does not require the commonly used coarse-to-fine warping strategy. It is based on a quadratic relaxation of the optical flow functional which decouples data term and regularizer in such a way that the non-linearized variational problem can be solved by an alternation of two globally optimal steps, one imposing optimal data consistency, the other imposing discontinuity-preserving regularity of the flow field. Experimental results confirm that the proposed algorithmic implementation out-performs the traditional warping strategy, in particular for the case of large displacements of small scale structures.

Original languageEnglish
Title of host publication2009 IEEE 12th International Conference on Computer Vision, ICCV 2009
Pages1609-1614
Number of pages6
DOIs
StatePublished - 2009
Externally publishedYes
Event12th International Conference on Computer Vision, ICCV 2009 - Kyoto, Japan
Duration: 29 Sep 20092 Oct 2009

Publication series

NameProceedings of the IEEE International Conference on Computer Vision

Conference

Conference12th International Conference on Computer Vision, ICCV 2009
Country/TerritoryJapan
CityKyoto
Period29/09/092/10/09

Fingerprint

Dive into the research topics of 'Large displacement optical flow computation without warping'. Together they form a unique fingerprint.

Cite this