EUVIMEDEUVIMED entdecken
Crossref

GenCAD-Self-Repairing: Latent Space Steering for Feasibility-Aware 3D Computer-Aided Design Generation

Chikaha Tsuji, Enrique Flores Medina, Harshit Gupta, Md Ferdous Alam

Journal of Computing and Information Science in Engineering · 01.06.2026 · 26 (6)

DOI: 10.1115/1.4071109 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computing and Information Science in Engineering, online erschienen am 15.05.2026. Verfasst von Chikaha Tsuji und 3 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advancements in generative artificial intelligence have shown strong potential for automating computer-aided design (CAD) generation. Unlike commonly used point cloud or mesh representations in 3D generation tasks, CAD models typically require editable and manufacturable boundary representations (B-reps) that satisfy strict geometric and topological constraints. However, due to the hierarchical structure of B-reps, generative CAD models often use network-friendly intermediate representations, such as CAD command sequences, rather than directly operating on B-reps. This introduces a fundamental limitation: generated representations are not guaranteed to be convertible into valid B-reps by the geometry kernel, as the generative model remains unaware of the kernel’s convertibility constraints during generation. In this work, we propose GenCAD-Self-Repairing, a feasibility-aware CAD generation framework that explicitly incorporates geometry-kernel convertibility into the generative process. Our approach operates entirely in the latent space and steers latent representations toward feasible regions through feasibility-guided diffusion denoising combined with a latent-space self-repair mechanism. Experimental results demonstrate that our method significantly improves CAD generation feasibility by reducing infeasible outputs by 56.9% relative to a state-of-the-art baseline, while largely preserving geometric accuracy.

Zitieren

APA

Tsuji, C., Medina, E. F., Gupta, H., & Alam, M. F. (2026). GenCAD-Self-Repairing: Latent Space Steering for Feasibility-Aware 3D Computer-Aided Design Generation. Journal of Computing and Information Science in Engineering, 26(6). https://doi.org/10.1115/1.4071109

Vancouver

Tsuji C, Medina EF, Gupta H, Alam MF. GenCAD-Self-Repairing: Latent Space Steering for Feasibility-Aware 3D Computer-Aided Design Generation. Journal of Computing and Information Science in Engineering. 2026;26(6). doi:10.1115/1.4071109

BibTeX
@article{Tsuji2026,
  author = {Tsuji, Chikaha and Medina, Enrique Flores and Gupta, Harshit and Alam, Md Ferdous},
  title = {GenCAD-Self-Repairing: Latent Space Steering for Feasibility-Aware 3D Computer-Aided Design Generation},
  journal = {Journal of Computing and Information Science in Engineering},
  year = {2026},
  volume = {26},
  number = {6},
  doi = {10.1115/1.4071109}
}
Kostenlos starten →