We are Jan Eric Kyprianidis (Hasso-Plattner-Institut, Germany) and Henry Kang (University of Missouri, St. Louis, USA). In this chapter we present a GPU implementation of the anisotropic Kuwahara filter. The anisotropic Kuwahara filter is a generalization of the Kuwahara filter that avoids artifacts by adapting shape, scale and orientation of the filter to the local structure of the input. Due to this adaption, directional image features are better preserved and emphasized. This results in overall sharper edges and a more feature-abiding painterly effect. Unlike existing nonlinear smoothing filters, the anisotropic Kuwahara filter is robust against high-contrast noise and avoids overblurring in low-contrast areas, providing a consistent level of abstraction across the image. It also ensures outstanding temporal coherence in video abstraction, even with per-frame filtering.Sunday, December 20, 2009
Anisotropic Kuwahara Filtering on the GPU
We are Jan Eric Kyprianidis (Hasso-Plattner-Institut, Germany) and Henry Kang (University of Missouri, St. Louis, USA). In this chapter we present a GPU implementation of the anisotropic Kuwahara filter. The anisotropic Kuwahara filter is a generalization of the Kuwahara filter that avoids artifacts by adapting shape, scale and orientation of the filter to the local structure of the input. Due to this adaption, directional image features are better preserved and emphasized. This results in overall sharper edges and a more feature-abiding painterly effect. Unlike existing nonlinear smoothing filters, the anisotropic Kuwahara filter is robust against high-contrast noise and avoids overblurring in low-contrast areas, providing a consistent level of abstraction across the image. It also ensures outstanding temporal coherence in video abstraction, even with per-frame filtering.
