Image and Video Abstraction by Anisotropic Kuwahara Filtering

Jan Eric Kyprianidis1       Henry Kang2       Jürgen Döllner1

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

Computer Graphics Forum, 28(7) - Pacific Graphics 2009


We present a non-photorealistic rendering technique to transform color images and videos into painterly abstractions. It is based on a generalization of the Kuwahara filter that is adapted to the local shape of features, derived from the smoothed structure tensor. Contrary to conventional edge-preserving filters, our filter generates a painting-like flattening effect along the local feature directions while preserving shape boundaries. As opposed to conventional painting algorithms, it produces temporally coherent video abstraction without extra processing. The GPU implementation of our method processes video in real-time. The results have the clearness of cartoon illustrations but also exhibit directional information as found in oil paintings.

DOI,   PDF,   Code


Gallery 1 thumbnail

Comparisons with other popular techniques.

Gallery 2 thumbnail

Comparison with Artistic Edge and Corner Preserving Smoothing.


Video 1 thumbnail

Video 1

Video 2 thumbnail

Video 2

Video 3 thumbnail

Video 3


Kyprianidis, J. E. Kang, H., & Döllner, J. (2009). Image and Video Abstraction by Anisotropic Kuwahara Filtering. Computer Graphics Forum, 28(7), pp. 1955-1963. (Special issue on Pacific Graphics 2009)

@ARTICLE{ Kyprianidis:2011:AKF,
  author  = { Kyprianidis, Jan Eric and Kang, Henry and D{\"o}llner, J{\"u}rgen },
  title   = { Image and Video Abstraction by Anisotropic Kuwahara Filtering },
  journal = { Computer Graphics Forum },
  number  = { 7 },
  volume  = { 28 },
  pages   = { 1955--1963 },
  year    = { 2009 },
  doi     = { 10.1111/j.1467-8659.2009.01574.x },
  note    = { Special issue on Pacific Graphics 2009 }