Smoothly Varying Affine Stitching

Wen-Yan Lin, Siying Liu, Yasuyuki Matsushita, Tian-Tsong Ng, Loong Fah Cheong

CVPR 2011 pp. 345-352

doi:10.1109/CVPR.2011.5995314 /cvpr/2011/lin2011cvpr-smoothly/

Abstract

Traditional image stitching using parametric transforms such as homography, only produces perceptually correct composites for planar scenes or parallax free camera motion between source frames. This limits mosaicing to source images taken from the same physical location. In this paper, we introduce a smoothly varying affine stitching field which is flexible enough to handle parallax while retaining the good extrapolation and occlusion handling properties of parametric transforms. Our algorithm which jointly estimates both the stitching field and correspondence, permits the stitching of general motion source images, provided the scenes do not contain abrupt protrusions.

PDF CVPR Semantic Scholar

Cite

Text

Lin et al. "Smoothly Varying Affine Stitching." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995314

Markdown

[Lin et al. "Smoothly Varying Affine Stitching." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/lin2011cvpr-smoothly/) doi:10.1109/CVPR.2011.5995314

BibTeX

@inproceedings{lin2011cvpr-smoothly,
  title     = {{Smoothly Varying Affine Stitching}},
  author    = {Lin, Wen-Yan and Liu, Siying and Matsushita, Yasuyuki and Ng, Tian-Tsong and Cheong, Loong Fah},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2011},
  pages     = {345-352},
  doi       = {10.1109/CVPR.2011.5995314},
  url       = {https://mlanthology.org/cvpr/2011/lin2011cvpr-smoothly/}
}