论文标题
PF-NET：3D点云完成的点分形网络
PF-Net: Point Fractal Network for 3D Point Cloud Completion
论文作者
论文摘要
在本文中，我们提出了一个点分形网络（PF-NET），这是一种基于学习的新型方法，用于精确和高保真点云完成。与现有的点云完成网络不同，该网络从不完整的点云中生成点云的整体形状，并始终更改现有点，并遇到噪声和几何损失，PF-net保留了不完整点云的空间布置，并且可以找出预测中缺失区域的详细几何结构。为了在此任务中取得成功，PF-NET通过利用基于功能点的多尺度生成网络来估算缺失点云。此外，我们总结了多阶段的完成损失和对抗性损失，以产生更现实的缺失区域。对抗性损失可以更好地解决预测中的多种模式。我们的实验证明了我们方法对几个具有挑战性的点云完成任务的有效性。
In this paper, we propose a Point Fractal Network (PF-Net), a novel learning-based approach for precise and high-fidelity point cloud completion. Unlike existing point cloud completion networks, which generate the overall shape of the point cloud from the incomplete point cloud and always change existing points and encounter noise and geometrical loss, PF-Net preserves the spatial arrangements of the incomplete point cloud and can figure out the detailed geometrical structure of the missing region(s) in the prediction. To succeed at this task, PF-Net estimates the missing point cloud hierarchically by utilizing a feature-points-based multi-scale generating network. Further, we add up multi-stage completion loss and adversarial loss to generate more realistic missing region(s). The adversarial loss can better tackle multiple modes in the prediction. Our experiments demonstrate the effectiveness of our method for several challenging point cloud completion tasks.
