Free-hand sketch synthesis with deformable stroke models
Abstract
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.
Download
[Paper]
[Bibtex]
[Code&Dataset]
An object&part annotation tool (involved in code, producing pascal voc annotation XML)
Result
Application
Synthesis results
