XDoG: advanced image stylization with eXtended Difference-of-Gaussians

Abstract

Recent extensions to the standard Difference-of-Gaussians (DoG) edge detection operator have rendered it less susceptible to noise and increased its aesthetic appeal for stylistic depiction applications. Despite these advances, the technical subtleties and stylistic potential of the DoG operator are often overlooked. This paper reviews the DoG operator, including recent improvements, and offers many new results spanning a variety of styles, including pencil-shading, pastel, hatching, and binary black-and-white images. Additionally, we demonstrate a range of subtle artistic effects, such as ghosting, speed-lines, negative edges, indication, and abstraction, and we explain how all of these are obtained without, or only with slight modifications to an extended DoG formulation. In all cases, the visual quality achieved by the extended DoG operator is comparable to or better than those of systems dedicated to a single style.