Duality TV-L1 flow with fundamental matrix prior

A. Wedel, T. Pock, J. Braun, U. Franke, D. Cremers

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

51 Scopus citations

Abstract

Variational techniques yield the most accurate results for dense optical flow fields between two images. They have the nice property of inherent smoothness to cope with untextured image regions: the filling-in of such regions is driven by neighbouring pixels. Such filling-in is not always the best choice. If the scene is mostly stationary and the camera is moving, the direction of the optical flow vectors can be restricted using the fundamental matrix. In this paper we propose an exact solution of the variational optical flow, using the fundamental matrix geometry as an additional weak prior. Our novel approach currently performs best on the Middlebury flow evaluation which includes images from stationary and dynamic scenes.

Original languageEnglish
Title of host publication2008 23rd International Conference Image and Vision Computing New Zealand, IVCNZ
DOIs
StatePublished - 2008
Externally publishedYes
Event2008 23rd International Conference Image and Vision Computing New Zealand, IVCNZ - Christchurch, New Zealand
Duration: 26 Nov 200828 Nov 2008

Publication series

Name2008 23rd International Conference Image and Vision Computing New Zealand, IVCNZ

Conference

Conference2008 23rd International Conference Image and Vision Computing New Zealand, IVCNZ
Country/TerritoryNew Zealand
CityChristchurch
Period26/11/0828/11/08

Keywords

  • Fundamental matrix
  • Optical flow
  • Optimization
  • Structure from motion
  • Total variation

Fingerprint

Dive into the research topics of 'Duality TV-L1 flow with fundamental matrix prior'. Together they form a unique fingerprint.

Cite this