DTGBrepGen: A Novel B-rep Generative Model through Decoupling Topology and Geometry

2025-03-17

AI Summary

Automated B-rep generation in CAD faces a fundamental trade-off between topological validity and geometric fidelity. To address this, we propose a topology–geometry decoupling framework: first, a two-stage graph modeling approach—encoding dual adjacency relations (edge–face and edge–vertex)—generates topologically valid structures; subsequently, a Transformer-based diffusion model progressively synthesizes geometric primitives—vertices, edges, and B-spline surfaces. This work constitutes the first explicit separation and joint optimization of topological and geometric modeling in B-rep generation. Our method integrates graph neural networks, diffusion probabilistic modeling, and B-spline parametric representation. Experiments on multiple CAD benchmarks demonstrate significant improvements: +28.6% topological validity rate and −37.2% Chamfer distance, while preserving realism, diversity, and industrial applicability of generated models.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Boundary representation (B-rep) of geometric models is a fundamental format in Computer-Aided Design (CAD). However, automatically generating valid and high-quality B-rep models remains challenging due to the complex interdependence between the topology and geometry of the models. Existing methods tend to prioritize geometric representation while giving insufficient attention to topological constraints, making it difficult to maintain structural validity and geometric accuracy. In this paper, we propose DTGBrepGen, a novel topology-geometry decoupled framework for B-rep generation that explicitly addresses both aspects. Our approach first generates valid topological structures through a two-stage process that independently models edge-face and edge-vertex adjacency relationships. Subsequently, we employ Transformer-based diffusion models for sequential geometry generation, progressively generating vertex coordinates, followed by edge geometries and face geometries which are represented as B-splines. Extensive experiments on diverse CAD datasets show that DTGBrepGen significantly outperforms existing methods in both topological validity and geometric accuracy, achieving higher validity rates and producing more diverse and realistic B-reps. Our code is publicly available at https://github.com/jinli99/DTGBrepGen.

Problem

• Automatically generating valid B-rep models in CAD
• Addressing complex topology-geometry interdependence
• Improving topological validity and geometric accuracy

Innovation

• Decouples topology and geometry in B-rep generation
• Uses Transformer-based diffusion for geometry modeling
• Two-stage process ensures topological validity