Abstract: A system and method for synthesizing painterly-looking images from input images (e.g., photographs). An input image is first interactively decomposed into a hierarchical representation of its constituent components named parse tree, whose nodes correspond to regions, curves, and objects in the image, with occlusion relations. According to semantic information in the parse tree, a sequence of brush strokes is automatically prepared according a brush dictionary manually built in advance, with their parameters in geometry and appearance appropriately tuned, and blended onto the canvas to generate a painterly-looking image.
Type:
Application
Filed:
November 23, 2011
Publication date:
May 31, 2012
Applicant:
LOTUS HILL INSTITUTE FOR COMPUTER VISION AND INFORMATION SCIENCE