Miao Yongwei, Zhang Lei, Liu Jiazong, Wang Jinrong, Liu Fuchang
IEEE Comput Graph Appl. 2021 May-Jun;41(3):20-33. doi: 10.1109/MCG.2021.3065533. Epub 2021 May 7.
Shape completion for 3-D point clouds is an important issue in the literature of computer graphics and computer vision. We propose an end-to-end shape-preserving point completion network through encoder-decoder architecture, which works directly on incomplete 3-D point clouds and can restore their overall shapes and fine-scale structures. To achieve this task, we design a novel encoder that encodes information from neighboring points in different orientations and scales, as well as a decoder that outputs dense and uniform complete point clouds. We augment a 3-D object dataset based on ModelNet40 and validate the effectiveness of our shape-preserving completion network. Experimental results demonstrate that the recovered point clouds lie close to ground truth points. Our method outperforms state-of-the-art approaches in terms of Chamfer distance (CD) error and earth mover's distance (EMD) error. Furthermore, our end-to-end completion network is robust to model noise, the different levels of incomplete data, and can also generalize well to unseen objects and real-world data.
三维点云的形状补全是计算机图形学和计算机视觉领域文献中的一个重要问题。我们通过编码器-解码器架构提出了一种端到端的形状保持点补全网络，该网络直接作用于不完整的三维点云，并能够恢复其整体形状和精细尺度结构。为了完成这项任务，我们设计了一种新颖的编码器，它对来自不同方向和尺度的相邻点的信息进行编码，以及一个解码器，其输出密集且均匀的完整点云。我们基于ModelNet40扩充了一个三维物体数据集，并验证了我们的形状保持补全网络的有效性。实验结果表明，恢复的点云与真实点接近。在倒角距离（CD）误差和推土机距离（EMD）误差方面，我们的方法优于当前的先进方法。此外，我们的端到端补全网络对模型噪声、不同程度的不完整数据具有鲁棒性，并且还能很好地推广到未见物体和真实世界数据。
