Li Jianxin, Si Guannan, Liang Xinyu, An Zhaoliang, Tian Pengxin, Zhou Fengyu
School of Electrical Engineering, Academy of Information Sciences, Shandong Jiaotong University, Jinan 250357, China.
School of Control Science and Engineering, Shandong University, Jinan 250012, China.
Entropy (Basel). 2023 Jul 2;25(7):1018. doi: 10.3390/e25071018.
In this paper, we propose a novel method for point cloud complementation called PADPNet. Our approach uses a combination of global and local information to infer missing elements in the point cloud. We achieve this by dividing the input point cloud into uniform local regions, called perceptual fields, which are abstractly understood as special convolution kernels. The set of point clouds in each local region is represented as a feature vector and transformed into N uniform perceptual fields as the input to our transformer model. We also designed a geometric density-aware block to better exploit the inductive bias of the point cloud's 3D geometric structure. Our method preserves sharp edges and detailed structures that are often lost in voxel-based or point-based approaches. Experimental results demonstrate that our approach outperforms other methods in reducing the ambiguity of output results. Our proposed method has important applications in 3D computer vision and can efficiently recover complete 3D object shapes from missing point clouds.
在本文中，我们提出了一种名为PADPNet的新颖的点云补全方法。我们的方法结合了全局和局部信息来推断点云中缺失的元素。我们通过将输入点云划分为均匀的局部区域（称为感知域）来实现这一点，这些感知域被抽象地理解为特殊的卷积核。每个局部区域中的点云集被表示为一个特征向量，并转换为N个均匀的感知域作为我们的Transformer模型的输入。我们还设计了一个几何密度感知模块，以更好地利用点云3D几何结构的归纳偏差。我们的方法保留了在基于体素或基于点的方法中经常丢失的锐利边缘和详细结构。实验结果表明，我们的方法在减少输出结果的模糊性方面优于其他方法。我们提出的方法在3D计算机视觉中具有重要应用，并且可以从缺失的点云中有效地恢复完整的3D物体形状。
