Less Redraw, More Explore: Suggestion and Completion for Sketch-to-Image

Zhao, Zeyu; Rees, Connor; Bailey, Gavin; Jones, Matt; Robinson, Simon; Pearson, Jen

doi:10.1145/3772318.3791026

Conference Paper/Proceeding/Abstract 551 views 15 downloads

Less Redraw, More Explore: Suggestion and Completion for Sketch-to-Image

Zeyu Zhao

, Connor Rees, Gavin Bailey

, Matt Jones

, Simon Robinson

, Jen Pearson

Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems, Pages: 1 - 11

Swansea University Authors: Zeyu Zhao , Connor Rees, Gavin Bailey , Matt Jones , Simon Robinson , Jen Pearson

DOI (Published version): 10.1145/3772318.3791026

Abstract

Sketch-to-image systems let users transform simple line drawings into realistic images, but current workflows force users into tedious redraw-regenerate cycles that slow creative exploration. We introduce two complementary interaction techniques that reduce iteration friction: AutoSketch, which exte...

Full description

Published in:	Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems
ISBN:	979-8-4007-2278-3
Published:	New York, NY, USA Association for Computing Machinery (ACM) 2026
URI:	https://cronfa.swan.ac.uk/Record/cronfa71270

first_indexed	2026-01-19T16:01:39Z
last_indexed	2026-05-16T05:20:43Z
id	cronfa71270
recordtype	SURis
fullrecord	<?xml version="1.0"?><rfc1807><datestamp>2026-05-15T12:54:24.4435471</datestamp><bib-version>v2</bib-version><id>71270</id><entry>2026-01-19</entry><title>Less Redraw, More Explore: Suggestion and Completion for Sketch-to-Image</title><swanseaauthors><author><sid>a2a323d3beb66a9219f02485a5aae787</sid><ORCID>0000-0002-4070-2694</ORCID><firstname>Zeyu</firstname><surname>Zhao</surname><name>Zeyu Zhao</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>09194a4c065f1ba507bc0723b1dabcc3</sid><ORCID/><firstname>Connor</firstname><surname>Rees</surname><name>Connor Rees</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>22a3941f1c07bf22a71a87d30b7d2d52</sid><ORCID>0000-0002-9445-9626</ORCID><firstname>Gavin</firstname><surname>Bailey</surname><name>Gavin Bailey</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>10b46d7843c2ba53d116ca2ed9abb56e</sid><ORCID>0000-0001-7657-7373</ORCID><firstname>Matt</firstname><surname>Jones</surname><name>Matt Jones</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>cb3b57a21fa4e48ec633d6ba46455e91</sid><ORCID>0000-0001-9228-006X</ORCID><firstname>Simon</firstname><surname>Robinson</surname><name>Simon Robinson</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>6d662d9e2151b302ed384b243e2a802f</sid><ORCID>0000-0002-1960-1012</ORCID><firstname>Jen</firstname><surname>Pearson</surname><name>Jen Pearson</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2026-01-19</date><deptcode>MACS</deptcode><abstract>Sketch-to-image systems let users transform simple line drawings into realistic images, but current workflows force users into tedious redraw-regenerate cycles that slow creative exploration. We introduce two complementary interaction techniques that reduce iteration friction: AutoSketch, which extends partial sketches through AI-driven completions (pre-generation support), and BackSketch, which transforms generated images back into editable sketches at multiple abstraction levels (post-generation support). In a study with 30 participants, the results indicate that both techniques can improve exploration and expressiveness compared to a baseline sketch-to-image system, while AutoSketch also can increase users’ sense of agency and co-creation with the AI. We contribute new evidence that shifting support before or after generation opens distinct pathways for balancing user control and system initiative. Together, our results establish pre- and post-generation assistance as a design space for co-creative sketch-to-image systems.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems</journal><volume/><journalNumber/><paginationStart>1</paginationStart><paginationEnd>11</paginationEnd><publisher>Association for Computing Machinery (ACM)</publisher><placeOfPublication>New York, NY, USA</placeOfPublication><isbnPrint/><isbnElectronic>979-8-4007-2278-3</isbnElectronic><issnPrint/><issnElectronic/><keywords>Generative AI, sketch-to-image, creativity, user interface, image generation, user study</keywords><publishedDay>13</publishedDay><publishedMonth>4</publishedMonth><publishedYear>2026</publishedYear><publishedDate>2026-04-13</publishedDate><doi>10.1145/3772318.3791026</doi><url/><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>This work was supported by Engineering and Physical Sciences Research Council grant EP/Y010477/1.</funders><projectreference/><lastEdited>2026-05-15T12:54:24.4435471</lastEdited><Created>2026-01-19T10:48:00.6791422</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Zeyu</firstname><surname>Zhao</surname><orcid>0000-0002-4070-2694</orcid><order>1</order></author><author><firstname>Connor</firstname><surname>Rees</surname><orcid/><order>2</order></author><author><firstname>Gavin</firstname><surname>Bailey</surname><orcid>0000-0002-9445-9626</orcid><order>3</order></author><author><firstname>Matt</firstname><surname>Jones</surname><orcid>0000-0001-7657-7373</orcid><order>4</order></author><author><firstname>Simon</firstname><surname>Robinson</surname><orcid>0000-0001-9228-006X</orcid><order>5</order></author><author><firstname>Jen</firstname><surname>Pearson</surname><orcid>0000-0002-1960-1012</orcid><order>6</order></author></authors><documents><document><filename>71270__36747__33ebf5fd9f064f3d938976c231472b22.pdf</filename><originalFilename>71270.VOR.pdf</originalFilename><uploaded>2026-05-15T12:50:50.3646759</uploaded><type>Output</type><contentLength>1806977</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© 2026 Copyright held by the owner/author(s). This work is licensed under a Creative Commons Attribution 4.0 International License.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling	2026-05-15T12:54:24.4435471 v2 71270 2026-01-19 Less Redraw, More Explore: Suggestion and Completion for Sketch-to-Image a2a323d3beb66a9219f02485a5aae787 0000-0002-4070-2694 Zeyu Zhao Zeyu Zhao true false 09194a4c065f1ba507bc0723b1dabcc3 Connor Rees Connor Rees true false 22a3941f1c07bf22a71a87d30b7d2d52 0000-0002-9445-9626 Gavin Bailey Gavin Bailey true false 10b46d7843c2ba53d116ca2ed9abb56e 0000-0001-7657-7373 Matt Jones Matt Jones true false cb3b57a21fa4e48ec633d6ba46455e91 0000-0001-9228-006X Simon Robinson Simon Robinson true false 6d662d9e2151b302ed384b243e2a802f 0000-0002-1960-1012 Jen Pearson Jen Pearson true false 2026-01-19 MACS Sketch-to-image systems let users transform simple line drawings into realistic images, but current workflows force users into tedious redraw-regenerate cycles that slow creative exploration. We introduce two complementary interaction techniques that reduce iteration friction: AutoSketch, which extends partial sketches through AI-driven completions (pre-generation support), and BackSketch, which transforms generated images back into editable sketches at multiple abstraction levels (post-generation support). In a study with 30 participants, the results indicate that both techniques can improve exploration and expressiveness compared to a baseline sketch-to-image system, while AutoSketch also can increase users’ sense of agency and co-creation with the AI. We contribute new evidence that shifting support before or after generation opens distinct pathways for balancing user control and system initiative. Together, our results establish pre- and post-generation assistance as a design space for co-creative sketch-to-image systems. Conference Paper/Proceeding/Abstract Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems 1 11 Association for Computing Machinery (ACM) New York, NY, USA 979-8-4007-2278-3 Generative AI, sketch-to-image, creativity, user interface, image generation, user study 13 4 2026 2026-04-13 10.1145/3772318.3791026 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University SU Library paid the OA fee (TA Institutional Deal) This work was supported by Engineering and Physical Sciences Research Council grant EP/Y010477/1. 2026-05-15T12:54:24.4435471 2026-01-19T10:48:00.6791422 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Zeyu Zhao 0000-0002-4070-2694 1 Connor Rees 2 Gavin Bailey 0000-0002-9445-9626 3 Matt Jones 0000-0001-7657-7373 4 Simon Robinson 0000-0001-9228-006X 5 Jen Pearson 0000-0002-1960-1012 6 71270__36747__33ebf5fd9f064f3d938976c231472b22.pdf 71270.VOR.pdf 2026-05-15T12:50:50.3646759 Output 1806977 application/pdf Version of Record true © 2026 Copyright held by the owner/author(s). This work is licensed under a Creative Commons Attribution 4.0 International License. true eng https://creativecommons.org/licenses/by/4.0/
title	Less Redraw, More Explore: Suggestion and Completion for Sketch-to-Image
spellingShingle	Less Redraw, More Explore: Suggestion and Completion for Sketch-to-Image Zeyu Zhao Connor Rees Gavin Bailey Matt Jones Simon Robinson Jen Pearson
title_short	Less Redraw, More Explore: Suggestion and Completion for Sketch-to-Image
title_full	Less Redraw, More Explore: Suggestion and Completion for Sketch-to-Image
title_fullStr	Less Redraw, More Explore: Suggestion and Completion for Sketch-to-Image
title_full_unstemmed	Less Redraw, More Explore: Suggestion and Completion for Sketch-to-Image
title_sort	Less Redraw, More Explore: Suggestion and Completion for Sketch-to-Image
author_id_str_mv	a2a323d3beb66a9219f02485a5aae787 09194a4c065f1ba507bc0723b1dabcc3 22a3941f1c07bf22a71a87d30b7d2d52 10b46d7843c2ba53d116ca2ed9abb56e cb3b57a21fa4e48ec633d6ba46455e91 6d662d9e2151b302ed384b243e2a802f
author_id_fullname_str_mv	a2a323d3beb66a9219f02485a5aae787_*_Zeyu Zhao 09194a4c065f1ba507bc0723b1dabcc3__Connor Rees 22a3941f1c07bf22a71a87d30b7d2d52__Gavin Bailey 10b46d7843c2ba53d116ca2ed9abb56e__Matt Jones cb3b57a21fa4e48ec633d6ba46455e91__Simon Robinson 6d662d9e2151b302ed384b243e2a802f_*_Jen Pearson
author	Zeyu Zhao Connor Rees Gavin Bailey Matt Jones Simon Robinson Jen Pearson
author2	Zeyu Zhao Connor Rees Gavin Bailey Matt Jones Simon Robinson Jen Pearson
format	Conference Paper/Proceeding/Abstract
container_title	Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems
container_start_page	1
publishDate	2026
institution	Swansea University
isbn	979-8-4007-2278-3
doi_str_mv	10.1145/3772318.3791026
publisher	Association for Computing Machinery (ACM)
college_str	Faculty of Science and Engineering
hierarchytype
hierarchy_top_id	facultyofscienceandengineering
hierarchy_top_title	Faculty of Science and Engineering
hierarchy_parent_id	facultyofscienceandengineering
hierarchy_parent_title	Faculty of Science and Engineering
department_str	School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str	1
active_str	0
description	Sketch-to-image systems let users transform simple line drawings into realistic images, but current workflows force users into tedious redraw-regenerate cycles that slow creative exploration. We introduce two complementary interaction techniques that reduce iteration friction: AutoSketch, which extends partial sketches through AI-driven completions (pre-generation support), and BackSketch, which transforms generated images back into editable sketches at multiple abstraction levels (post-generation support). In a study with 30 participants, the results indicate that both techniques can improve exploration and expressiveness compared to a baseline sketch-to-image system, while AutoSketch also can increase users’ sense of agency and co-creation with the AI. We contribute new evidence that shifting support before or after generation opens distinct pathways for balancing user control and system initiative. Together, our results establish pre- and post-generation assistance as a design space for co-creative sketch-to-image systems.
published_date	2026-04-13T17:18:10Z
_version_	1866630839988649984
score	11.106612

Less Redraw, More Explore: Suggestion and Completion for Sketch-to-Image

Similar Items