Image and Video Abstraction by Coherence-Enhancing Filtering

Abstract

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

Images

Gallery of example images

Videos

Video 1

Citation

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 }
}