Learning CAD Modeling Sequences via Projection and Part Awareness

Yang Liu, Daxuan Ren, Yijie Ding, Jianmin Zheng, Fang Deng

Keywords: Computer-Aided Design, Modeling Sequence Generation, Semi-Autoregressive, Part Awareness, Triplane Projection

Abstract: This paper presents PartCAD, a novel framework for reconstructing CAD modeling sequences directly from point clouds by projection-guided, part-aware geometry reasoning. It consists of (1) an autoregressive approach that decomposes point clouds into part-aware latent representations, serving as interpretable anchors for CAD generation; (2) a projection guidance module that provides explicit cues about underlying design intent via triplane projections; and (3) a non-autoregressive decoder to generate sketch-extrusion parameters in a single forward pass, enabling efficient and structurally coherent CAD instruction synthesis. By bridging geometric signals and semantic understanding, PartCAD tackles the challenge of reconstructing editable CAD models—capturing underlying design processes—from 3D point clouds. Extensive experiments show that PartCAD significantly outperforms existing methods for CAD instruction generation in both accuracy and robustness. The work sheds light on part-driven reconstruction of interpretable CAD models, opening new avenues in reverse engineering and CAD automation.

Primary Area: Deep learning (e.g., architectures, generative models, optimization for deep networks, foundation models, LLMs)

Submission Number: 6232