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

要旨

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.

著者
Zeyu Zhao
Swansea University, Swansea, United Kingdom
Connor Rees
Swansea University, Swansea, United Kingdom
Gavin Bailey
Swansea University, Swansea, United Kingdom
Matt Jones
Swansea University, Swansea, United Kingdom
Simon Robinson
Swansea University, Swansea, United Kingdom
Jennifer Pearson
Swansea University, Swansea, Wales, United Kingdom

会議: CHI 2026

ACM CHI Conference on Human Factors in Computing Systems

セッション: Generative AI and Creative Workflows

P1 - Room 123
6 件の発表
2026-04-14 20:15:00
2026-04-14 21:45:00