Research

Paper

AI LLM March 19, 2026

Sketch2Topo: Using Hand-Drawn Inputs for Diffusion-Based Topology Optimization

Authors

Shuyue Feng, Cedric Caremel, Yoshihiro Kawahara

Abstract

Topology optimization (TO) is employed in engineering to optimize structural performance while maximizing material efficiency. However, traditional TO methods incur significant computational and time costs. Although research has leveraged generative AI to predict TO outcomes and validated feasibility and accuracy, existing approaches still suffer from limited customizability and impose a high cognitive load on users. Furthermore, balancing structural performance with aesthetic attributes remains a persistent challenge. We developed Sketch2Topo, which augments a diffusion-based TO model with image-to-image generation and image editing capabilities. With Sketch2Topo, users can use sketching to customize geometries and specify physical constraints. The tool also supports mask input, enabling users to perform TO on selected regions only, thereby supporting higher levels of customization. We summarize the workflow and details of the tool and conduct a brief quantitative evaluation. Finally, we explore application scenarios and discuss how hand-drawn input improves usability while balancing functionality and aesthetics.

Metadata

arXiv ID: 2603.18960
Provider: ARXIV
Primary Category: cs.HC
Published: 2026-03-19
Fetched: 2026-03-20 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.18960v1</id>\n    <title>Sketch2Topo: Using Hand-Drawn Inputs for Diffusion-Based Topology Optimization</title>\n    <updated>2026-03-19T14:26:25Z</updated>\n    <link href='https://arxiv.org/abs/2603.18960v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.18960v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Topology optimization (TO) is employed in engineering to optimize structural performance while maximizing material efficiency. However, traditional TO methods incur significant computational and time costs. Although research has leveraged generative AI to predict TO outcomes and validated feasibility and accuracy, existing approaches still suffer from limited customizability and impose a high cognitive load on users. Furthermore, balancing structural performance with aesthetic attributes remains a persistent challenge. We developed Sketch2Topo, which augments a diffusion-based TO model with image-to-image generation and image editing capabilities. With Sketch2Topo, users can use sketching to customize geometries and specify physical constraints. The tool also supports mask input, enabling users to perform TO on selected regions only, thereby supporting higher levels of customization. We summarize the workflow and details of the tool and conduct a brief quantitative evaluation. Finally, we explore application scenarios and discuss how hand-drawn input improves usability while balancing functionality and aesthetics.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.HC'/>\n    <published>2026-03-19T14:26:25Z</published>\n    <arxiv:comment>5 pages, 4 figures, accepted at CHI 2026 as a poster</arxiv:comment>\n    <arxiv:primary_category term='cs.HC'/>\n    <author>\n      <name>Shuyue Feng</name>\n    </author>\n    <author>\n      <name>Cedric Caremel</name>\n    </author>\n    <author>\n      <name>Yoshihiro Kawahara</name>\n    </author>\n    <arxiv:doi>10.1145/3772363.3798434</arxiv:doi>\n    <link href='https://doi.org/10.1145/3772363.3798434' rel='related' title='doi'/>\n  </entry>"
}