Universal Sketch Perceptual Grouping

Ke Li, Kaiyue Pang, Jifei Song, Yi-Zhe Song, Tao Xiang, Timothy Hospedales, Honggang Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

In this work we aim to develop a universal sketch grouper. That is, a grouper that can be applied to sketches of any category in any domain to group constituent strokes/segments into semantically meaningful object parts. The first obstacle to this goal is the lack of large-scale datasets with grouping annotation. To overcome this, we contribute the largest sketch perceptual grouping (SPG) dataset to date, consisting of 20, 000 unique sketches evenly distributed over 25 object categories. Furthermore, we propose a novel deep universal perceptual grouping model. The model is learned with both generative and discriminative losses. The generative losses improve the generalisation ability of the model to unseen object categories and datasets. The discriminative losses include a local grouping loss and a novel global grouping loss to enforce global grouping consistency. We show that the proposed model significantly outperforms the state-of-the-art groupers. Further, we show that our grouper is useful for a number of sketch analysis tasks including sketch synthesis and fine-grained sketch-based image retrieval (FG-SBIR).
Original languageEnglish
Title of host publicationEuropean Conference on Computer Vision (ECCV 2018)
Place of PublicationMunich, Germany
PublisherSpringer, Cham
Pages593-609
Number of pages16
ISBN (Electronic)978-3-030-01237-3
ISBN (Print)978-3-030-01236-6
DOIs
Publication statusPublished - 7 Oct 2018
EventEuropean Conference on Computer Vision 2018 - Munich, Germany
Duration: 8 Sept 201814 Sept 2018
https://eccv2018.org/

Publication series

NameLecture Notes in Computer Science
PublisherSpringer, Cham
Volume11212
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameImage Processing, Computer Vision, Pattern Recognition, and Graphics
Volume11212

Conference

ConferenceEuropean Conference on Computer Vision 2018
Abbreviated titleECCV 2018
Country/TerritoryGermany
CityMunich
Period8/09/1814/09/18
Internet address

Fingerprint

Dive into the research topics of 'Universal Sketch Perceptual Grouping'. Together they form a unique fingerprint.

Cite this