Locally Non-Rigid Registration for Mobile HDR Photography

Orazio Gallo, Alejandro J. Troccoli, Jun Hu, Kari Pulli, Jan Kautz

CVPRW 2015 pp. 48-55

doi:10.1109/CVPRW.2015.7301366 /cvprw/2015/gallo2015cvprw-locally/

Abstract

Image registration for stack-based HDR photography is challenging. If not properly accounted for, camera motion and scene changes result in artifacts in the composite image. Unfortunately, existing methods to address this problem are either accurate, but too slow for mobile devices, or fast, but prone to failing. We propose a method that fills this void: our approach is extremely fast - under 700ms on a commercial tablet for a pair of 5MP images - and prevents the artifacts that arise from insufficient registration quality.

PDF CVPRW Semantic Scholar

Cite

Text

Gallo et al. "Locally Non-Rigid Registration for Mobile HDR Photography." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2015. doi:10.1109/CVPRW.2015.7301366

Markdown

[Gallo et al. "Locally Non-Rigid Registration for Mobile HDR Photography." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2015.](https://mlanthology.org/cvprw/2015/gallo2015cvprw-locally/) doi:10.1109/CVPRW.2015.7301366

BibTeX

@inproceedings{gallo2015cvprw-locally,
  title     = {{Locally Non-Rigid Registration for Mobile HDR Photography}},
  author    = {Gallo, Orazio and Troccoli, Alejandro J. and Hu, Jun and Pulli, Kari and Kautz, Jan},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2015},
  pages     = {48-55},
  doi       = {10.1109/CVPRW.2015.7301366},
  url       = {https://mlanthology.org/cvprw/2015/gallo2015cvprw-locally/}
}