Free-hand Sketch Synthesis with Deformable Stroke Models
This work addresses the challenge of generating realistic free-hand sketches for applications in digital art and design, representing an incremental improvement in sketch synthesis.
The authors tackled the problem of automatically summarizing and synthesizing free-hand sketches by developing a generative model that learns stroke composition and part structure from sketch collections, enabling the synthesis of visually similar sketches.
We present a generative model which can automatically summarize the stroke composition of free-hand sketches of a given category. When our model is fit to a collection of sketches with similar poses, it discovers and learns the structure and appearance of a set of coherent parts, with each part represented by a group of strokes. It represents both consistent (topology) as well as diverse aspects (structure and appearance variations) of each sketch category. Key to the success of our model are important insights learned from a comprehensive study performed on human stroke data. By fitting this model to images, we are able to synthesize visually similar and pleasant free-hand sketches.