View2CAD: Parsing Multi-view into CAD Command Sequences

Computer-aided design (CAD) is the primary and indispensable tool for engineers and designers, streamlining design processes and contributing to innovation in various industries. However, mastering these complex CAD programs demands extensive training and experience for CAD practitioners. To this end, this paper proposes View2CAD to reconstruct CAD models from multi-view. Specifically, we first introduce a novel end-to-end network that directly reconstructs parametric CAD command sequences from multi-view images. Then, the proposed View2CAD solves the problem of the low-rank bottle in the traditional attention mechanism of neural networks. Finally, a new parametric CAD dataset is presented, in which we add multi-view images for the corresponding CAD sequence and remove redundant CAD data. The comparison experiments demonstrate that our View2CAD framework is capable of reconstructing high-quality parametric CAD models, which can be further edited by other users in collaborative CAD/CAM environment.