Deep learning with 3D data has progressed significantly since the introduction of convolutional neural networks that can handle point order ambiguity in point cloud data. While being able to achieve good accuracies in various scene understanding tasks, previous methods often have low training speed and complex network architecture. In this paper, we address these problems by proposing an efficient endto-end permutation invariant convolution for point cloud deep learning. Our simple yet effective convolution operator named ShellConv uses statistics from concentric spherical shells to define representative features and resolve the point order ambiguity, allowing traditional convolution to perform on such features. Based on ShellConv we further build an efficient neural network named ShellNet to directly consume the point clouds with larger receptive fields while maintaining less layers. We demonstrate the efficacy of ShellNet by producing state-of-the-art results on object classification, object part segmentation, and semantic scene segmentation while keeping the network very fast to train. Our code is publicly available in our project page 1 .

Recent progresses in 3D deep learning has shown that it is possible to design special convolution operators to consume point cloud data. However, a typical drawback is that rotation invariance is often not guaranteed, resulting in networks that generalizes poorly to arbitrary rotations. In this paper, we introduce a novel convolution operator for point clouds that achieves rotation invariance. Our core idea is to use lowlevel rotation invariant geometric features such as distances and angles to design a convolution operator for point cloud learning. The well-known point ordering problem is also addressed by a binning approach seamlessly built into the convolution. This convolution operator then serves as the basic building block of a neural network that is robust to point clouds under 6-DoF transformations such as translation and rotation. Our experiment shows that our method performs with high accuracy in common scene understanding tasks such as object classification and segmentation. Compared to previous and concurrent works, most importantly, our method is able to generalize and achieve consistent results across different scenarios in which training and testing can contain arbitrary rotations. Our implementation is publicly available at our project page 1 .

Solvothermal reactions of [Et(4)N][Tp*WS(3)(CuCl)(3)] (1) (Tp* = hydridotris(3,5-dimethylpyrazol-1-yl)borate) with CuCN and KCu(CN)(2) afforded two [Tp*WS(3)Cu(3)]-based coordination polymers [Tp*WS(3)Cu(3)(μ(3)-DMF){Cu(CN)(3)}](2) (2) and K[Tp*WS(3)Cu(3)(μ(3)-DMF){Cu(2)(CN)(4.5)}](2) (3). The third-order NLO and PL responses of 1 were activated and greatly amplified through its assembly via the [Cu(CN)(3)](2-) and [Cu(4)(CN)(9)](5-) species in 2 and 3.

No abstract

No abstract