Image and Video Abstraction by Anisotropic Kuwahara Filtering

Abstract

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.