GraphCAD creates accurate CAD models using graph-based geometry diffusion
GraphCAD: Geometry-Aware Diffusion on Edge-Adjacency Graphs for CAD Generation
Computer Vision and Pattern Recognition
Summary
Generating detailed CAD models is hard because designs combine precise shapes and complex connections. The authors created GraphCAD, a tool that represents CAD designs as special graphs focusing on edges and their relationships. This lets GraphCAD model both the shape and connections together, improving the quality of generated CAD models. They also built a large dataset to help test their approach and showed it outperforms older methods for making complex designs.
What this means in practice
- •For cad software developers: Integrate a graph-based generative model that improves automatic creation of complex CAD designs with better geometric accuracy.$Commercial implications: Enables new CAD features to generate high-fidelity models for engineers and designers, creating marketable software enhancements.
- •For mechanical engineers: Use generative models grounded in geometry and topology to accelerate conceptual design phases with reliable 3D CAD prototypes.
Authors
Wenhao Zheng, Xianggen Liu, Li Yue, Jiancheng Shi, Jiancheng Lv
Abstract
Generative modeling for Computer-Aided Design (CAD) remains fundamentally challenged by the need to capture the intricate interplay between discrete topological connectivity and precise spatial geometry inherent in Boundary Representations (B-reps). Existing generative approaches largely formulate CAD construction as a sequence modeling problem, but consequently lack an explicit topological inductive bias. In this work, we present GraphCAD, a geometry-aware generative framework that centers modeling on the Edge-Adjacency Graph (EAG), a novel graph-based CAD representation tailored for generative tasks. GraphCAD adopts a hybrid graph diffusion formulation to jointly model the discrete and continuous components of EAG and introduces a geometry-aware denoising mechanism that renders node attributes into spatial point sets. These point sets are encoded by an SE(3)-equivariant backbone and fused into the node representations, thereby grounding the generative process in physical geometry. To support this study, we construct EAGBench, a large-scale dataset of engineering CAD models. Extensive experiments show that GraphCAD can generate complex CAD models with more than 50 faces and achieves state-of-the-art performance in geometric fidelity and distributional alignment compared with sequence-based baselines.