CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Jianyu, Wang, Yizhou, Yue, Xiangyu, Ma, Xinzhu, Guo, Jingyang, Zhou, Dongzhan, Ouyang, Wanli, Tang, Shixiang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918115616489472
author Wu, Jianyu
Wang, Yizhou
Yue, Xiangyu
Ma, Xinzhu
Guo, Jingyang
Zhou, Dongzhan
Ouyang, Wanli
Tang, Shixiang
author_facet Wu, Jianyu
Wang, Yizhou
Yue, Xiangyu
Ma, Xinzhu
Guo, Jingyang
Zhou, Dongzhan
Ouyang, Wanli
Tang, Shixiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_20830
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generation
Wu, Jianyu
Wang, Yizhou
Yue, Xiangyu
Ma, Xinzhu
Guo, Jingyang
Zhou, Dongzhan
Ouyang, Wanli
Tang, Shixiang
Computer Vision and Pattern Recognition
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.
title CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.20830