Portrait painting using active templates

Abstract

Portraiture plays a substantial role in traditional painting, yet it has not been studied in depth in painterly rendering research. The difficulty in rendering human portraits is due to our acute visual perception to the structure of human face. To achieve satisfactory results, a portrait rendering algorithm should account for facial structure. In this paper, we present an example-based method to render portrait paintings from photographs, by transferring brush strokes from previously painted portrait templates by artists. These strokes carry rich information about not only the facial structure but also how artists depict the structure with large and decisive brush strokes and vibrant colors. With a dictionary of portrait painting templates for different types of faces, we show that this method can produce satisfactory results.