Image and Video Abstraction by Coherence-Enhancing Filtering

Jan Eric Kyprianidis1       Henry Kang2

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

Computer Graphics Forum, 30(2) - Proceedings Eurographics 2011

Teaser image


In this work, we present a non-photorealistic rendering technique to create stylized abstractions from color images and videos. Our approach is based on adaptive line integral convolution in combination with directional shock filtering. The smoothing process regularizes directional image features while the shock filter provides a sharpening effect. Both operations are guided by a flow field derived from the structure tensor. To obtain a high-quality flow field, we present a novel smoothing scheme for the structure tensor based on Poisson's equation. Our approach effectively regularizes anisotropic image regions while preserving the overall image structure and achieving a consistent level of abstraction. Moreover, it is suitable for per-frame filtering of video and can be efficiently implemented to process content in real-time.

DOI,   PDF,   Code


Gallery 1 thumbnail

Gallery of example images

Gallery 2 thumbnail

Comparisons with other techniques


Video 1 thumbnail

Video 1

Video 2 thumbnail

Video 2


Kyprianidis, J. E. & Kang, H. (2011). Image and Video Abstraction by Coherence-Enhancing Filtering. Computer Graphics Forum, 30(2), pp. 593-602. (Proceedings Eurographics 2011)

@ARTICLE{ Kyprianidis:2011:CEF,
  author  = { Kyprianidis, Jan Eric and Kang, Henry },
  title   = { Image and Video Abstraction by Coherence-Enhancing Filtering },
  journal = { Computer Graphics Forum },
  number  = { 2 },
  volume  = { 30 },
  pages   = { 593-–602 },
  year    = { 2011 },
  doi     = { 10.1111/j.1467-8659.2011.01882.x },
  note    = { Proceedings Eurographics 2011 }