HoLa: B-Rep Generation using a Holistic Latent Representation
ACM Transactions on Graphics · 01.08.2025 · 44 (4) · 1-25
DOI: 10.1145/3730842 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 27.07.2025. Verfasst von Yilin Liu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: National Key R&D Program of China, ICFCRT, Guangdong Basic and Applied Basic Research Foundation.
Abstract (Originalsprache)
We introduce a novel representation for learning and generating Computer-Aided Design (CAD) models in the form of boundary representations (B-Reps). Our representation unifies the continuous geometric properties of B-Rep primitives in different orders (e.g., surfaces and curves) and their discrete topological relations in a holistic latent (HoLa) space. This is based on the simple observation that the topological connection between two surfaces is intrinsically tied to the geometry of their intersecting curve. Such a prior allows us to reformulate topology learning in B-Reps as a geometric reconstruction problem in Euclidean space. Specifically, we eliminate the presence of curves, vertices, and all the topological connections in the latent space by learning to distinguish and derive curve geometries from a pair of surface primitives via a neural intersection network. To this end, our holistic latent space is only defined on surfaces but encodes a full B-Rep model, including the geometry of surfaces, curves, vertices, and their topological relations. Our compact and holistic latent space facilitates the design of a first diffusion-based generator to take on a large variety of inputs including point clouds, single/multi-view images, 2D sketches, and text prompts. Our method significantly reduces ambiguities, redundancies, and incoherences among the generated B-Rep primitives, as well as training complexities inherent in prior multi-step B-Rep learning pipelines, while achieving greatly improved validity rate over current state of the art: 82% vs. ≈50%.
Förderung
- National Key R&D Program of China
- ICFCRT
- Guangdong Basic and Applied Basic Research Foundation
- Shenzhen Science and Technology Program
Zitieren
APA
Liu, Y., Xu, D., Yu, X., Xu, X., Cohen-Or, D., Zhang, H., & Huang, H. (2025). HoLa: B-Rep Generation using a Holistic Latent Representation. ACM Transactions on Graphics, 44(4), 1-25. https://doi.org/10.1145/3730842
Vancouver
Liu Y, Xu D, Yu X, Xu X, Cohen-Or D, Zhang H, et al. HoLa: B-Rep Generation using a Holistic Latent Representation. ACM Transactions on Graphics. 2025;44(4):1-25. doi:10.1145/3730842
BibTeX
@article{Liu2025,
author = {Liu, Yilin and Xu, Duoteng and Yu, Xingyao and Xu, Xiang and Cohen-Or, Daniel and Zhang, Hao and Huang, Hui},
title = {HoLa: B-Rep Generation using a Holistic Latent Representation},
journal = {ACM Transactions on Graphics},
year = {2025},
volume = {44},
number = {4},
pages = {1--25},
doi = {10.1145/3730842}
}
EUVIMED