University of Surrey

Test tubes in the lab Research in the ATI Dance Research

SketchHealer A Graph-to-Sequence Network for Recreating Partial Human Sketches

Su, Guoyao, Qi, Yonggang, Pang, Kaiyue, Yang, Jie and Song, Yi-Zhe (2020) SketchHealer A Graph-to-Sequence Network for Recreating Partial Human Sketches In: The 31st British Machine Vision Conference (BMVC 2020), 07-10 Sep 2020, Online (virtual).

[img]
Preview
Text
SketchHealer - VoR.pdf - Version of Record

Download (11MB) | Preview

Abstract

To perceive and create a whole from parts is a prime trait of the human visual system. In this paper, we teach machines to perform a similar task by recreating a vectorised human sketch from its incomplete parts. This is fundamentally different to prior work on image completion (i) sketches exhibit a severe lack of visual cue and are of a sequential nature, and more importantly (ii) we ask for an agent that does not just fill in a missing part, but to recreate a novel sketch that closely resembles the partial input from scratch. Central to our contribution is a graph model that encodes both the visual and structural features over multiple categories. A novel sketch graph construction module is proposed that leverages the sequential nature of sketches to associate key parts centred around stroke junctions. The intuition is then that message passing within the said graph will naturally provide the healing power when it comes to missing parts (nodes). Finally, an off-the-shelf LSTM-based decoder is employed to decode sketches in a vectorised fashion. Both qualitative and quantitative results show that the proposed model significantly outperforms state-of-the-art alternatives.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Su, Guoyao
Qi, YonggangYonggang.qi@surrey.ac.uk
Pang, Kaiyue
Yang, Jie
Song, Yi-Zhey.song@surrey.ac.uk
Date : 2020
Copyright Disclaimer : © BMVC 2020. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.
Related URLs :
Depositing User : Clive Harris
Date Deposited : 07 Oct 2020 09:27
Last Modified : 07 Oct 2020 09:27
URI: http://epubs.surrey.ac.uk/id/eprint/858690

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