A nonlocal gradient concentration method for image smoothing

Qian Liu, Caiming Zhang, Qiang Guo, Yuanfeng ZhouComputational 2015 · DOI

Abstract

It is challenging to consistently smooth natural images, yet smoothing results determine the quality of a broad range of applications in computer vision. To achieve consistent smoothing, we propose a novel optimization model making use of the redundancy of natural images, by defining a nonlocal concentration regularization term on the gradient. This nonlocal constraint is carefully combined with a gradient-sparsity constraint, allowing details throughout the whole image to be removed automatically in a data-driven manner. As variations in gradient between similar patches can be suppressed effectively, the new model has excellent edge preserving, detail removal, and visual consistency properties. Comparisons with state-of-the-art smoothing methods demonstrate the effectiveness of the new method. Several applications, including edge manipulation, image abstraction, detail magnification, and image resizing, show the applicability of the new method.
BibTeX
@inproceedings{liu2015nonlocal,
  author = {Qian Liu and Caiming Zhang and Qiang Guo and Yuanfeng Zhou},
  title = {{A nonlocal gradient concentration method for image smoothing}},
  booktitle = {Computational},
  year = {2015},
  doi = {10.1007/s41095-015-0012-6},
}

Loading related content...

Figure