Institute Homepage
Institute Homepage DE Sign In

Back

Autonomous Vision Conference Paper 2019

Taking a Deeper Look at the Inverse Compositional Algorithm

Thumb ticker sm img 20180102 213454
Perceiving Systems, Autonomous Vision
Zhaoyang Lv
Thumb ticker sm upper body tiny
Autonomous Vision, Perceiving Systems
Andreas Geiger
Guest Scientist
Lv

In this paper, we provide a modern synthesis of the classic inverse compositional algorithm for dense image alignment. We first discuss the assumptions made by this well-established technique, and subsequently propose to relax these assumptions by incorporating data-driven priors into this model. More specifically, we unroll a robust version of the inverse compositional algorithm and replace multiple components of this algorithm using more expressive models whose parameters we train in an end-to-end fashion from data. Our experiments on several challenging 3D rigid motion estimation tasks demonstrate the advantages of combining optimization with learning-based techniques, outperforming the classic inverse compositional algorithm as well as data-driven image-to-pose regression approaches.

Author(s): Zhaoyang Lv and Frank Dellaert and James M. Rehg and Andreas Geiger
Book Title: Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)
Year: 2019
Month: June
Bibtex Type: Conference Paper (inproceedings)
Event Name: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019
Event Place: Long Beach, USA
Electronic Archiving: grant_archive
Links:

BibTex 

@inproceedings{Lv2019CVPR,
  title = {Taking a Deeper Look at the Inverse Compositional Algorithm},
  booktitle = {Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
  abstract = {In this paper, we provide a modern synthesis of the classic inverse compositional algorithm for dense image alignment. We first discuss the assumptions made by this well-established technique, and subsequently propose to relax these assumptions by incorporating data-driven priors into this model. More specifically, we unroll a robust version of the inverse compositional algorithm and replace multiple components of this algorithm using more expressive models whose parameters we train in an end-to-end fashion from data. Our experiments on several challenging 3D rigid motion estimation tasks demonstrate the advantages of combining optimization with learning-based techniques, outperforming the classic inverse compositional algorithm as well as data-driven image-to-pose regression approaches.},
  month = jun,
  year = {2019},
  slug = {lv2019cvpr},
  author = {Lv, Zhaoyang and Dellaert, Frank and Rehg, James M. and Geiger, Andreas},
  month_numeric = {6}
}