Taking a Deeper Look at the Inverse Compositional Algorithm

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.

Cite

Text

Lv et al. "Taking a Deeper Look at the Inverse Compositional Algorithm." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00471

Markdown

[Lv et al. "Taking a Deeper Look at the Inverse Compositional Algorithm." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/lv2019cvpr-taking/) doi:10.1109/CVPR.2019.00471

BibTeX

@inproceedings{lv2019cvpr-taking,
  title     = {{Taking a Deeper Look at the Inverse Compositional Algorithm}},
  author    = {Lv, Zhaoyang and Dellaert, Frank and Rehg, James M. and Geiger, Andreas},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2019},
  doi       = {10.1109/CVPR.2019.00471},
  url       = {https://mlanthology.org/cvpr/2019/lv2019cvpr-taking/}
}