Video Magnification in Presence of Large Motions

Mohamed Elgharib, Mohamed Hefeeda, Fredo Durand, William T. Freeman

CVPR 2015

doi:10.1109/CVPR.2015.7299039 /cvpr/2015/elgharib2015cvpr-video/

Abstract

Video magnification reveals subtle variations that would be otherwise invisible to the naked eye. Current techniques require all motion in the video to be very small, which is unfortunately not always the case. Tiny yet meaningful motions are often combined with larger motions, such as the small vibrations of a gate as it rotates, or the microsaccades in a moving eye. We present a layer-based video magnification approach that can amplify small motions within large ones. An examined region/layer is temporally aligned and subtle variations are magnified. Matting is used to magnify only region of interest while maintaining integrity of nearby sites. Results show handling larger motions, larger amplification factors and significant reduction in artifacts over state of the art.

PDF CVPR Semantic Scholar

Cite

Text

Elgharib et al. "Video Magnification in Presence of Large Motions." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7299039

Markdown

[Elgharib et al. "Video Magnification in Presence of Large Motions." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/elgharib2015cvpr-video/) doi:10.1109/CVPR.2015.7299039

BibTeX

@inproceedings{elgharib2015cvpr-video,
  title     = {{Video Magnification in Presence of Large Motions}},
  author    = {Elgharib, Mohamed and Hefeeda, Mohamed and Durand, Fredo and Freeman, William T.},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2015},
  doi       = {10.1109/CVPR.2015.7299039},
  url       = {https://mlanthology.org/cvpr/2015/elgharib2015cvpr-video/}
}