ML Anthology

Local Cross-Modality Image Alignment Using Unsupervised Learning

Öjvind Bernander, Christof Koch
ECCV 1990 pp. 573-575
doi:10.1007/BFB0014910 /eccv/1990/bernander1990eccv-local/

Abstract

We propose a method for automatically aligning images with local distortions from different sensors, using real images instead of calibration objects. The algorithm has three components. First, we extract intensity discontinuities, because this is a feature that is likely to show up across modalities. Second, we use a correlation scheme that averages over time rather than space, for high precision. Third, we propose an architecture and a learning scheme that learn the correlation surfaces over time and implement the image coordinate transform.

PDF ECCV Semantic Scholar

Cite

Text

Bernander and Koch. "Local Cross-Modality Image Alignment Using Unsupervised Learning." European Conference on Computer Vision, 1990. doi:10.1007/BFB0014910

Markdown

[Bernander and Koch. "Local Cross-Modality Image Alignment Using Unsupervised Learning." European Conference on Computer Vision, 1990.](https://mlanthology.org/eccv/1990/bernander1990eccv-local/) doi:10.1007/BFB0014910

BibTeX

@inproceedings{bernander1990eccv-local,
  title     = {{Local Cross-Modality Image Alignment Using Unsupervised Learning}},
  author    = {Bernander, Öjvind and Koch, Christof},
  booktitle = {European Conference on Computer Vision},
  year      = {1990},
  pages     = {573-575},
  doi       = {10.1007/BFB0014910},
  url       = {https://mlanthology.org/eccv/1990/bernander1990eccv-local/}
}