BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patch
ACM Transactions on Graphics · 2025-12 · 44 (6) · 1-18
DOI: 10.1145/3763323 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 04.12.2025. Verfasst von Pu Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 95 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing Natural Science Foundation, Strategic Priority Research Program of the Chinese Academy of Sciences.
Abstract (Originalsprache)
Boundary representation (B-rep) is the de facto standard for CAD model representation in modern industrial design. The intricate coupling between geometric and topological elements in B-rep structures has forced existing generative methods to rely on cascaded multi-stage networks, resulting in error accumulation and computational inefficiency. We present BrepGPT, a single-stage autoregressive framework for B-rep generation. Our key innovation lies in the Voronoi Half-Patch (VHP) representation, which decomposes B-reps into unified local units by assigning geometry to nearest half-edges and sampling their next pointers. Unlike hierarchical representations that require multiple distinct encodings for different structural levels, our VHP representation facilitates unifying geometric attributes and topological relations in a single, coherent format. We further leverage dual VQ-VAEs to encode both vertex topology and Voronoi Half-Patches into vertex-based tokens, achieving a more compact sequential encoding. A decoder-only Transformer is then trained to autoregressively predict these tokens, which are subsequently mapped to vertex-based features and decoded into complete B-rep models. Experiments demonstrate that BrepGPT achieves state-of-the-art performance in unconditional B-rep generation. The framework also exhibits versatility in various applications, including conditional generation from category labels, point clouds, text descriptions, and images, as well as B-rep autocompletion and interpolation.
Förderung
- National Natural Science Foundation of China
- Beijing Natural Science Foundation
- Strategic Priority Research Program of the Chinese Academy of Sciences
- Guangdong Basic and Applied Basic Research Foundation
- King Abdullah University of Science and Technology (KAUST) - Center of Excellence for Generative AI
Zitieren
APA
Li, P., Zhang, W., Quan, W., Zhang, B., Wonka, P., & Yan, D. (2025). BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patch. ACM Transactions on Graphics, 44(6), 1-18. https://doi.org/10.1145/3763323
Vancouver
Li P, Zhang W, Quan W, Zhang B, Wonka P, Yan D. BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patch. ACM Transactions on Graphics. 2025;44(6):1-18. doi:10.1145/3763323
BibTeX
@article{Li2025,
author = {Li, Pu and Zhang, Wenhao and Quan, Weize and Zhang, Biao and Wonka, Peter and Yan, Dongming},
title = {BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patch},
journal = {ACM Transactions on Graphics},
year = {2025},
volume = {44},
number = {6},
pages = {1--18},
doi = {10.1145/3763323}
}
EUVIMED