Analyzing Spatially-Varying Blur

Ayan Chakrabarti, Todd E. Zickler, William T. Freeman

CVPR 2010 pp. 2512-2519

doi:10.1109/CVPR.2010.5539954 /cvpr/2010/chakrabarti2010cvpr-analyzing/

Abstract

Blur is caused by a pixel receiving light from multiple scene points, and in many cases, such as object motion, the induced blur varies spatially across the image plane. However, the seemingly straight-forward task of estimating spatially-varying blur from a single image has proved hard to accomplish reliably. This work considers such blur and makes two contributions: a local blur cue that measures the likelihood of a small neighborhood being blurred by a candidate blur kernel; and an algorithm that, given an image, simultaneously selects a motion blur kernel and segments the region that it affects. The methods are shown to perform well on a diversity of images.

PDF CVPR Semantic Scholar

Cite

Text

Chakrabarti et al. "Analyzing Spatially-Varying Blur." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5539954

Markdown

[Chakrabarti et al. "Analyzing Spatially-Varying Blur." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/chakrabarti2010cvpr-analyzing/) doi:10.1109/CVPR.2010.5539954

BibTeX

@inproceedings{chakrabarti2010cvpr-analyzing,
  title     = {{Analyzing Spatially-Varying Blur}},
  author    = {Chakrabarti, Ayan and Zickler, Todd E. and Freeman, William T.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2010},
  pages     = {2512-2519},
  doi       = {10.1109/CVPR.2010.5539954},
  url       = {https://mlanthology.org/cvpr/2010/chakrabarti2010cvpr-analyzing/}
}