Home
Uni-Logo
 

Large displacement optical flow

Thomas Brox, C. Bregler, J. Malik
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2009
Abstract: The literature currently provides two ways to establish point correspondences between images with moving objects. On one side, there are energy minimization methods that yield very accurate, dense flow fields, but fail as displacements get too large. On the other side, there is descriptor matching that allows for large displacements, but correspondences are very sparse, have limited accuracy, and due to missing regularity constraints there are many outliers. In this paper we propose a method that can combine the advantages of both matching strategies. A region hierarchy is established for both images. Descriptor matching on these regions provides a sparse set of hypotheses for correspondences. These are integrated into a variational approach and guide the local optimization to large displacement solutions. The variational optimization selects among the hypotheses and provides dense and subpixel accurate estimates, making use of geometric constraints and all available image information.
Downloads

Other associated files : brox_cvpr09.pdf [3.8MB]  

Images and movies

 

BibTex reference

@InProceedings{Bro09b,
  author       = "T. Brox and C. Bregler and J. Malik",
  title        = "Large displacement optical flow",
  booktitle    = "IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)",
  month        = "Jun.",
  year         = "2009",
  url          = "http://lmbweb.informatik.uni-freiburg.de/Publications/2009/Bro09b"
}

Other publications in the database