University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Sketchyscene: Richly-annotated scene sketches

Zou, C., Yu, Q., Du, R., Mo, H., Song, Yi-Zhe, Xiang, T., Gao, C., Chen, B. and Zhang, H. (2018) Sketchyscene: Richly-annotated scene sketches In: European Conference on Computer Vision (ECCV 2018), 08-14 Sep 2018, Munich, Germany.

Full text not available from this repository.


We contribute the first large-scale dataset of scene sketches, SketchyScene, with the goal of advancing research on sketch understanding at both the object and scene level. The dataset is created through a novel and carefully designed crowdsourcing pipeline, enabling users to efficiently generate large quantities of realistic and diverse scene sketches. SketchyScene contains more than 29,000 scene-level sketches, 7,000+ pairs of scene templates and photos, and 11,000+ object sketches. All objects in the scene sketches have ground-truth semantic and instance masks. The dataset is also highly scalable and extensible, easily allowing augmenting and/or changing scene composition. We demonstrate the potential impact of SketchyScene by training new computational models for semantic segmentation of scene sketches and showing how the new dataset enables several applications including image retrieval, sketch colorization, editing, and captioning, etc. The dataset and code can be found at

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
Zou, C.
Yu, Q.
Du, R.
Mo, H.
Xiang, T.
Gao, C.
Chen, B.
Zhang, H.
Date : 7 October 2018
DOI : 10.1007/978-3-030-01267-0_26
Uncontrolled Keywords : Scene sketch; Sketch dataset; Sketch segmentation
Related URLs :
Depositing User : Clive Harris
Date Deposited : 30 Jul 2019 13:15
Last Modified : 30 Jul 2019 13:15

Actions (login required)

View Item View Item


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