University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Learning Deep Sketch Abstraction

Muhammad, U.R., Yang, Y., Song, Yi-Zhe, Xiang, T. and Hospedales, T.M. (2019) Learning Deep Sketch Abstraction In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 18-22 Jun 2018, Salt Lake City, Utah.

[img]
Preview
Text
1804.04804.pdf - Accepted version Manuscript

Download (4MB) | Preview

Abstract

Human free-hand sketches have been studied in various contexts including sketch recognition, synthesis and fine-grained sketch-based image retrieval (FG-SBIR). A fundamental challenge for sketch analysis is to deal with drastically different human drawing styles, particularly in terms of abstraction level. In this work, we propose the first stroke-level sketch abstraction model based on the insight of sketch abstraction as a process of trading off between the recognizability of a sketch and the number of strokes used to draw it. Concretely, we train a model for abstract sketch generation through reinforcement learning of a stroke removal policy that learns to predict which strokes can be safely removed without affecting recognizability. We show that our abstraction model can be used for various sketch analysis tasks including: (1) modeling stroke saliency and understanding the decision of sketch recognition models, (2) synthesizing sketches of variable abstraction for a given category, or reference object instance in a photo, and (3) training a FG-SBIR model with photos only, bypassing the expensive photo-sketch pair collection step.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Muhammad, U.R.
Yang, Y.
Song, Yi-Zhey.song@surrey.ac.uk
Xiang, T.
Hospedales, T.M.
Date : February 2019
DOI : 10.1109/CVPR.2018.00836
OA Location : http://openaccess.thecvf.com/content_cvpr_2018/html/Muhammad_Learning_Deep_Sketch_CVPR_2018_paper.html
Copyright Disclaimer : © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Related URLs :
Additional Information : Printed proceedings for this conference are available from Curran Associates Inc. at http://www.proceedings.com/42520.html
Depositing User : Clive Harris
Date Deposited : 28 Jun 2019 13:16
Last Modified : 28 Jun 2019 13:16
URI: http://epubs.surrey.ac.uk/id/eprint/852103

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800