Advanced

Shift-map Image Registration

Svärm, Linus LU and Strandmark, Petter LU (2010) Swedish Symposium on Image Analysis (SSBA) 2010
Abstract
Shift-map image processing is a new framework based on energy minimization over a large space of labels. The optimization utilizes $\alpha$-expansion moves and iterative refinement over a Gaussian pyramid. In this paper we extend the range of applications to image registration.

To do this, new data and smoothness terms have to be constructed. We note a great improvement when we measure pixel similarities with the dense \daisy\ descriptor. The main contributions of this paper are:



* The extension of the shift-map framework to include image registration. We register images for which \sift\ only provides 3 correct matches.



* The first publicly available implementation of shift-map image... (More)
Shift-map image processing is a new framework based on energy minimization over a large space of labels. The optimization utilizes $\alpha$-expansion moves and iterative refinement over a Gaussian pyramid. In this paper we extend the range of applications to image registration.

To do this, new data and smoothness terms have to be constructed. We note a great improvement when we measure pixel similarities with the dense \daisy\ descriptor. The main contributions of this paper are:



* The extension of the shift-map framework to include image registration. We register images for which \sift\ only provides 3 correct matches.



* The first publicly available implementation of shift-map image processing (e.g. inpainting, registration).



We conclude by comparing shift-map registration to a recent method for optical flow with favorable results. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to conference
publication status
unpublished
subject
conference name
Swedish Symposium on Image Analysis (SSBA) 2010
language
English
LU publication?
yes
id
ae1d6e0a-c0f0-404d-aba1-2d19c854f704 (old id 1554167)
date added to LUP
2010-03-12 14:24:14
date last changed
2016-07-06 08:01:52
@misc{ae1d6e0a-c0f0-404d-aba1-2d19c854f704,
  abstract     = {Shift-map image processing is a new framework based on energy minimization over a large space of labels. The optimization utilizes $\alpha$-expansion moves and iterative refinement over a Gaussian pyramid. In this paper we extend the range of applications to image registration. <br/><br>
To do this, new data and smoothness terms have to be constructed. We note a great improvement when we measure pixel similarities with the dense \daisy\ descriptor. The main contributions of this paper are:<br/><br>
<br/><br>
 * The extension of the shift-map framework to include image registration. We register images for which \sift\ only provides 3 correct matches.<br/><br>
<br/><br>
 * The first publicly available implementation of shift-map image processing (e.g. inpainting, registration).<br/><br>
<br/><br>
We conclude by comparing shift-map registration to a recent method for optical flow with favorable results.},
  author       = {Svärm, Linus and Strandmark, Petter},
  language     = {eng},
  title        = {Shift-map Image Registration},
  year         = {2010},
}