ML Anthology

Automatic Removal of Chromatic Aberration from a Single Image

Sing Bing Kang
CVPR 2007
doi:10.1109/CVPR.2007.383214 /cvpr/2007/kang2007cvpr-automatic/

Abstract

Many high resolution images exhibit chromatic aberration (CA), where the color channels appear shifted. Unfortunately, merely compensating for these shifts is sometimes inadequate, because the intensities are modified by other effects such as spatially-varying defocus and (surprisingly) in-camera sharpening. In this paper, we start from the basic principles of image formation to characterize CA, and show how its effects can be substantially reduced. We also show results of CA correction on a number of high-resolution images taken with different cameras.

CVPR Semantic Scholar

Cite

Text

Kang. "Automatic Removal of Chromatic Aberration from a Single Image." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007. doi:10.1109/CVPR.2007.383214

Markdown

[Kang. "Automatic Removal of Chromatic Aberration from a Single Image." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007.](https://mlanthology.org/cvpr/2007/kang2007cvpr-automatic/) doi:10.1109/CVPR.2007.383214

BibTeX

@inproceedings{kang2007cvpr-automatic,
  title     = {{Automatic Removal of Chromatic Aberration from a Single Image}},
  author    = {Kang, Sing Bing},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2007},
  doi       = {10.1109/CVPR.2007.383214},
  url       = {https://mlanthology.org/cvpr/2007/kang2007cvpr-automatic/}
}