Free-Hand Sketch Synthesis with Deformable Stroke Models

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 repr...

Full description

Saved in:
Bibliographic Details
Published in:International journal of computer vision 2017-03, Vol.122 (1), p.169-190
Main Authors: Li, Yi, Song, Yi-Zhe, Hospedales, Timothy M., Gong, Shaogang
Format: Article
Language:English
Subjects:
Artificial Intelligence
Categories
Coherence
Collection
Computer Imaging
Computer Science
Computer vision
Datasets
Human performance
Image Processing and Computer Vision
Image retrieval
Learning
Motion detectors
Pattern Recognition
Pattern Recognition and Graphics
Semantics
Sketches
Strokes
Studies
Synthesis
Vision
Vision systems
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-016-0963-9