CoSketcher: Collaborative and Iterative Sketch Generation with LLMs under Linguistic and Spatial Control

Simple item page
dc.contributor.authorMei, Liwenen_US
dc.contributor.authorGuan, Manhaoen_US
dc.contributor.authorZheng, Yifanen_US
dc.contributor.authorZhang, Dongliangen_US
dc.contributor.editorChristie, Marcen_US
dc.contributor.editorHan, Ping-Hsuanen_US
dc.contributor.editorLin, Shih-Syunen_US
dc.contributor.editorPietroni, Nicoen_US
dc.contributor.editorSchneider, Teseoen_US
dc.contributor.editorTsai, Hsin-Rueyen_US
dc.contributor.editorWang, Yu-Shuenen_US
dc.contributor.editorZhang, Eugeneen_US
dc.date.accessioned2025-10-07T06:04:49Z
dc.date.available2025-10-07T06:04:49Z
dc.date.issued2025
dc.description.abstractSketching serves as both a medium for visualizing ideas and a process for creative iteration. While early neural sketch generation methods rely on category-specific data and lack generalization and iteration capability, recent advances in Large Language Models (LLMs) have opened new possibilities for more flexible and semantically guided sketching. In this work, we present CoSketcher, a controllable and iterative sketch generation system that leverages the prior knowledge and textual reasoning abilities of LLMs to align with the creative iteration process of human sketching. CoSketcher introduces a novel XML-style sketch language that represents stroke-level information in structured format, enabling the LLM to plan and generate complex sketches under both linguistic and spatial control. The system supports visual appealing sketch construction, including skeleton-contour decomposition for volumetric shapes and layout-aware reasoning for object relationships. Through extensive evaluation, we demonstrate that our method generates expressive sketches across both in-distribution and out-of-distribution categories, while also supporting scene-level composition and controllable iteration. Our method establishes a new paradigm for controllable sketch generation using off-the-shelf LLMs, with broad implications for creative human-AI collaboration.en_US
dc.description.sectionheadersInteraction & Virtual Reality
dc.description.seriesinformationPacific Graphics Conference Papers, Posters, and Demos
dc.identifier.doi10.2312/pg.20251298
dc.identifier.isbn978-3-03868-295-0
dc.identifier.pages12 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20251298
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pg20251298
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Human-centered computing → Human computer interaction (HCI)
dc.subjectHuman centered computing → Human computer interaction (HCI)
dc.titleCoSketcher: Collaborative and Iterative Sketch Generation with LLMs under Linguistic and Spatial Controlen_US
Files
Original bundle
Now showing 1 - 4 of 4
Thumbnail Image
Name:
pg20251298.pdf
Size:
33.32 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
paper1256_mm1.pdf
Size:
6.74 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1256_mm2.mp4
Size:
25.91 MB
Format:
Video MP4
Download
No Thumbnail Available
Name:
paper1256_mm3.zip
Size:
3.15 MB
Format:
Zip file
Download
Collections
PG2025 Conference Papers, Posters, and Demos