Image Abstraction by Structure Adaptive Filtering

Abstract

In this work we present a framework of automatic non-photorealistic image processing techniques that create simplified stylistic illustrations from color images, videos and 3D renderings. To smooth low-contrast regions while preserving edges, we present a new fast separated implementation of the bilateral filter. Our approach works by filtering in direction of the gradient and then filtering the intermediate result in perpendicular direction. When applied iteratively, our approach does not suffer from horizontal or vertical artifacts and creates smooth output at curved boundaries. To extract salient important edges we first apply a one-dimensional difference-of-Gaussians filter in direction of the gradient and then apply smoothing along a flow field which we derive from the smoothed structure tensor. Our method creates smooth coherent output for line and curve segments.