arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.02638cs.CV
收藏

P2CADNet:一个从点云重建参数化 3D CAD 模型的端到端重建网络

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

School of Computer Science, Wuhan University(武汉大学计算机学院)

Zhihao Zong, Fazhi He, Rubin Fan, Yuxin Liu

AI总结:

本文提出 P2CADNet,通过点云特征提取、双 transformer 解码器序列重建和交叉注意力参数优化,实现首个从点云端到端重建带特征参数化 CAD 模型的网络。

摘要:

计算机辅助设计(CAD),尤其是基于特征的参数化 CAD,在现代工业和社会中发挥着重要作用。然而,带特征 CAD 模型的重建比其他 CAD 模型的重建更具挑战性。为此,本文提出了一个从点云重建带特征 CAD 模型的端到端网络(P2CADNet)。首先,所提出的 P2CADNet 架构结合了点云特征提取器、CAD 序列重建器和参数优化器。随后,为了以自回归方式重建带特征 CAD 模型,CAD 序列重建器采用两个 transformer 解码器,一个带有目标掩码,另一个不带掩码。最后,为了更精确地预测参数,我们设计了一个具有交叉注意力机制的参数优化器,以进一步细化 CAD 特征参数。我们在公共数据集上评估了 P2CADNet,实验结果表明 P2CADNet 具有优异的重建质量和准确性。据我们所知,P2CADNet 是首个从点云重建带特征 CAD 模型的端到端网络,并可被视为未来工作的基线。因此,我们在 https://github.com/Blice0415/P2CADNet 开源了源代码。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑