Affine Steerers for Structured Keypoint Description

Abstract

We propose a way to train deep learning based keypoint descriptors that makes them approximately equivariant for locally affine transformations of the image plane. The main idea is to use the representation theory of GL(2) to generalize the recently introduced concept of steerers from rotations to affine transformations. Affine steerers give high control over how keypoint descriptions transform under image transformations. We demonstrate the potential of using this control for image matching. Finally, we propose a way to finetune keypoint descriptors with a set of steerers on upright images and obtain state-of-the-art results on several standard benchmarks. Code will be published at github.com/georg-bn/affine-steerers.

Cite

Text

Bökman et al. "Affine Steerers for Structured Keypoint Description." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-73016-0_26

Markdown

[Bökman et al. "Affine Steerers for Structured Keypoint Description." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/bokman2024eccv-affine/) doi:10.1007/978-3-031-73016-0_26

BibTeX

@inproceedings{bokman2024eccv-affine,
  title     = {{Affine Steerers for Structured Keypoint Description}},
  author    = {Bökman, Georg and Edstedt, Johan and Felsberg, Michael and Kahl, Fredrik},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2024},
  doi       = {10.1007/978-3-031-73016-0_26},
  url       = {https://mlanthology.org/eccv/2024/bokman2024eccv-affine/}
}