CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generation
This work addresses the problem of multimodal CAD generation for industrial design and manufacturing, offering incremental advancements in method and dataset.
The paper tackles the challenge of accurate and user-friendly Computer-Aided Design (CAD) generation by proposing CMT, a multimodal framework based on Boundary Representation (B-Rep), and introduces a large-scale dataset mmABC with over 1.3 million models. Results show improvements such as +10.68% in Coverage and +10.3% in Valid ratio for unconditional generation and +4.01 Chamfer for image-conditioned generation compared to state-of-the-art methods.
While accurate and user-friendly Computer-Aided Design (CAD) is crucial for industrial design and manufacturing, existing methods still struggle to achieve this due to their over-simplified representations or architectures incapable of supporting multimodal design requirements. In this paper, we attempt to tackle this problem from both methods and datasets aspects. First, we propose a cascade MAR with topology predictor (CMT), the first multimodal framework for CAD generation based on Boundary Representation (B-Rep). Specifically, the cascade MAR can effectively capture the ``edge-counters-surface'' priors that are essential in B-Reps, while the topology predictor directly estimates topology in B-Reps from the compact tokens in MAR. Second, to facilitate large-scale training, we develop a large-scale multimodal CAD dataset, mmABC, which includes over 1.3 million B-Rep models with multimodal annotations, including point clouds, text descriptions, and multi-view images. Extensive experiments show the superior of CMT in both conditional and unconditional CAD generation tasks. For example, we improve Coverage and Valid ratio by +10.68% and +10.3%, respectively, compared to state-of-the-art methods on ABC in unconditional generation. CMT also improves +4.01 Chamfer on image conditioned CAD generation on mmABC.