P2CADNet: An End-to-End Reconstruction Network for Parametric 3D CAD Model from Point Clouds

TL;DR

This paper introduces P2CADNet, an innovative end-to-end neural network that reconstructs feature-rich parametric 3D CAD models directly from point clouds, enhancing accuracy and serving as a baseline for future research.

Contribution

It presents the first end-to-end network for reconstructing featured CAD models from point clouds, combining transformers and a parameter optimizer for improved accuracy.

Findings

P2CADNet achieves high reconstruction quality and accuracy.

The model outperforms existing methods on the public dataset.

Open-sourced code facilitates future research in CAD reconstruction.

Abstract

Computer Aided Design (CAD), especially the feature-based parametric CAD, plays an important role in modern industry and society. However, the reconstruction of featured CAD model is more challenging than the reconstruction of other CAD models. To this end, this paper proposes an end-to-end network to reconstruct featured CAD model from point cloud (P2CADNet). Initially, the proposed P2CADNet architecture combines a point cloud feature extractor, a CAD sequence reconstructor and a parameter optimizer. Subsequently, in order to reconstruct the featured CAD model in an autoregressive way, the CAD sequence reconstructor applies two transformer decoders, one with target mask and the other without mask. Finally, for predicting parameters more precisely, we design a parameter optimizer with cross-attention mechanism to further refine the CAD feature parameters. We evaluate P2CADNet on the public dataset, and the experimental results show that P2CADNet has excellent reconstruction quality and accuracy. To our best knowledge, P2CADNet is the first end-to-end network to reconstruct featured CAD model from point cloud, and can be regarded as baseline for future works. Therefore, we open the source code at https://github.com/Blice0415/P2CADNet.