Structure from Multiple 2D Affine Correspondences Without Camera Calibration
Abstract
Image motion induced by camera or object motion can be approximated locally by an affine coordinate transformation. We extract 3D information directly from the affine parameters, without camera calibration. The derivation relies on the following assumptions: the object is rigid locally planar, and its local 3D motion is translation. These assumptions enable complete recovery of 3D structure, whereas it is impossible to compute the direction (and magnitude) of the motion. Still, it is possible to distinguish between objects moving differently. Explicit expressions for the structure and the motion indicators are given in terms of the 6 affine parameters, computed for each image patch. Results of experiments on data with known ground truth are described.
Cite
Text
Schweitzer and Krishnan. "Structure from Multiple 2D Affine Correspondences Without Camera Calibration." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996. doi:10.1109/CVPR.1996.517083Markdown
[Schweitzer and Krishnan. "Structure from Multiple 2D Affine Correspondences Without Camera Calibration." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996.](https://mlanthology.org/cvpr/1996/schweitzer1996cvpr-structure/) doi:10.1109/CVPR.1996.517083BibTeX
@inproceedings{schweitzer1996cvpr-structure,
title = {{Structure from Multiple 2D Affine Correspondences Without Camera Calibration}},
author = {Schweitzer, Haim and Krishnan, Radha},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {1996},
pages = {258-263},
doi = {10.1109/CVPR.1996.517083},
url = {https://mlanthology.org/cvpr/1996/schweitzer1996cvpr-structure/}
}