Image and Video Abstraction by Anisotropic Kuwahara Filtering

Jan Eric Kyprianidis1       Henry Kang2       Jürgen Döllner1

1Hasso-Plattner-Institut, Germany
2University of Missouri, St. Louis

In 7th Symposium on Non-Photorealistic Animation and Rendering (NPAR), Poster Session, 2009

Abstract

We present a generalization of the Kuwahara filter that avoids clustering artifacts by adapting shape, scale and orientation of the filter to the local structure of the input. Due to this adaption of the filter to the local structure, directional image features are better preserved and emphasized. This results in overall sharper edges and a more feature-abiding painterly effect. Local orientation and a measure for the anisotropy are derived from the eigenvalues and eigenvectors of the smoothed structure tensor. Then structure-aware smoothing is performed using a novel nonlinear filter. This nonlinear filter uses weighting functions defined over sectors of an ellipse whose shape is based on the local orientation and anisotropy. The filter response is defined as a weighed sum of the local averages where more weight is given to those averages with low standard deviation. Our approach shows excellent temporal coherence without requiring expensive video motion estimation. Implemented on the GPU the algorithm processes video in real-time.

PDF PDF (3.6 MB)

Images

Photograph courtesy http://philip.greenspun.com
Result
Original from USC-SIPI Image Database
Result
Original from USC-SIPI Image Database
Result
Photograph courtesy http://philip.greenspun.com
Result
Photograph courtesy http://philip.greenspun.com
Result
Photograph courtesy http://philip.greenspun.com
Result
Photograph courtesy http://philip.greenspun.com
Result

Video

NPAR 2009 Video

Citation

Kyprianidis, J. E., Kang, H., & Döllner, J. (2009). In 7th Symposium on Non-Photorealistic Animation and Rendering (NPAR), Poster Session.

@inproceedings{ kyprianidis-npar2009,
  author    = { Kyprianidis, Jan Eric and Kang, Henry and D{\"o}llner, J{\"u}rgen },
  title     = { Image and Video Abstraction by Anisotropic Kuwahara Filtering },
  booktitle = { 7th Symposium on Non-Photorealistic Animation and Rendering (NPAR), 
                Poster Session },
  year      = { 2009 }
}

Related

  • Kyprianidis, J. E., Kang, H., & Döllner, J. (2009). Image and Video Abstraction by Anisotropic Kuwahara Filtering. Computer Graphics Forum 28, 7. (Special issue on Pacific Graphics 2009)
  • Kyprianidis, J. E., Kang, H., & Döllner, J. (2010). Anisotropic Kuwahara Filtering on the GPU. In W. Engel (Ed.), GPU Pro – Advanced Rendering Techniques. AK Peters.