Reconstruct PFCAD Models with Dual-Transformer and Continuation Attention

On the one hand, parametric and feature-based design (PFDesign) is one of key techniques in today's CAD/CAM enterprises. On the other hand, the challenges in reconstruction of parametric and feature-based CAD models (PFCAD models) are quite different from that in reconstruction of geometry models (such as 3D mesh or B-rep models) in the previous studies. In this paper, we propose a novel architecture with dual-transformer and continuation attention to reconstruct PFCAD models. Specifically, our architecture contains a representation extractor module for discrete 3D data (such as mesh, point cloud, voxel), a dual-transformer reconstructor module for CAD operations and an adaptor module with CAD continuation attention for CAD pa-rameters. The proposed dual-transformer reconstructor includes two decoders, one is global decoder and the other is local decoder. Thus, we can leverage the whole design history as well as detail information to build PFCAD models. In addition, we devise a parameter adaptor with CAD continuation attention mechanism to further refine the CAD operation parameters. We conduct extensive experiments, in which the proposed approach achieves excellent or competitive results when compared to typical works in leading publications.