Real-Time Image Abstraction by Directed Filtering

Abstract

In this chapter we present a framework of automatic image processing techniques that create high-quality, simplified, stylistic illustrations from color images, videos, and 3D renderings. Our method extends the approach of Winnemöller et al. (2006) to use iterated bilateral filtering for abstraction and difference-of-Gaussians (DoG) for edge detection. We present enhancements to these techniques to improve the quality of the output by adapting them to the local orientation of the input.

Kyprianidis, J. E. & Döllner, J. (2009). Real-Time Image Abstraction by Directed Filtering. In W. Engel (Ed.), ShaderX7 – Advanced Rendering Techniques. Charles River Media.

@incollection{ kyprianidis-shaderx7,
  author    = { Kyprianidis, J. E. and D{\"o}llner, J. },
  title     = { Real-Time Image Abstraction by Directed Filtering },
  booktitle = { ShaderX7 - Advanced Rendering Techniques },
  publisher = { Charles River Media },
  editor    = { Engel, W. },
  year      = {2009}
}