适当的重量初始化是成功培训神经网络的重要意义。最近，批量归一化通过基于批处理统计数据量化每层来判定权重初始化的作用。遗憾的是，批量归一化在应用于小批量尺寸时具有多个缺点，因为在点云上学习时需要应对内存限制。虽然良好的重量初始化策略可以不需要呈现批量归一化，从而避免这些缺点，没有提出这种方法对于点卷积网络。为了填补这一差距，我们提出了一个框架来统一众多持续卷积。这实现了我们的主要贡献，方差感知权重初始化。我们表明，此初始化可以避免批量标准化，同时实现相似，并且在某些情况下更好的性能。

Unlike images which are represented in regular dense grids, 3D point clouds are irregular and unordered, hence applying convolution on them can be difficult. In this paper, we extend the dynamic filter to a new convolution operation, named PointConv. PointConv can be applied on point clouds to build deep convolutional networks. We treat convolution kernels as nonlinear functions of the local coordinates of 3D points comprised of weight and density functions. With respect to a given point, the weight functions are learned with multi-layer perceptron networks and density functions through kernel density estimation. The most important contribution of this work is a novel reformulation proposed for efficiently computing the weight functions, which allowed us to dramatically scale up the network and significantly improve its performance. The learned convolution kernel can be used to compute translation-invariant and permutation-invariant convolution on any point set in the 3D space. Besides, PointConv can also be used as deconvolution operators to propagate features from a subsampled point cloud back to its original resolution. Experiments on ModelNet40, ShapeNet, and ScanNet show that deep convolutional neural networks built on PointConv are able to achieve state-of-the-art on challenging semantic segmentation benchmarks on 3D point clouds. Besides, our experiments converting CIFAR-10 into a point cloud showed that networks built on PointConv can match the performance of convolutional networks in 2D images of a similar structure.

We present Kernel Point Convolution 1 (KPConv), a new design of point convolution, i.e. that operates on point clouds without any intermediate representation. The convolution weights of KPConv are located in Euclidean space by kernel points, and applied to the input points close to them. Its capacity to use any number of kernel points gives KP-Conv more flexibility than fixed grid convolutions. Furthermore, these locations are continuous in space and can be learned by the network. Therefore, KPConv can be extended to deformable convolutions that learn to adapt kernel points to local geometry. Thanks to a regular subsampling strategy, KPConv is also efficient and robust to varying densities. Whether they use deformable KPConv for complex tasks, or rigid KPconv for simpler tasks, our networks outperform state-of-the-art classification and segmentation approaches on several datasets. We also offer ablation studies and visualizations to provide understanding of what has been learned by KPConv and to validate the descriptive power of deformable KPConv.

3D点云的卷积经过广泛研究，但在几何深度学习中却远非完美。卷积的传统智慧在3D点之间表现出特征对应关系，这是对差的独特特征学习的内在限制。在本文中，我们提出了自适应图卷积（AGCONV），以供点云分析的广泛应用。 AGCONV根据其动态学习的功能生成自适应核。与使用固定/各向同性核的解决方案相比，AGCONV提高了点云卷积的灵活性，有效，精确地捕获了不同语义部位的点之间的不同关系。与流行的注意力体重方案不同，AGCONV实现了卷积操作内部的适应性，而不是简单地将不同的权重分配给相邻点。广泛的评估清楚地表明，我们的方法优于各种基准数据集中的点云分类和分割的最新方法。同时，AGCONV可以灵活地采用更多的点云分析方法来提高其性能。为了验证其灵活性和有效性，我们探索了基于AGCONV的完成，DeNoing，Upsmpling，注册和圆圈提取的范式，它们与竞争对手相当甚至优越。我们的代码可在https://github.com/hrzhou2/adaptconv-master上找到。

We present an approach to semantic scene analysis using deep convolutional networks. Our approach is based on tangent convolutions -a new construction for convolutional networks on 3D data. In contrast to volumetric approaches, our method operates directly on surface geometry. Crucially, the construction is applicable to unstructured point clouds and other noisy real-world data. We show that tangent convolutions can be evaluated efficiently on large-scale point clouds with millions of points. Using tangent convolutions, we design a deep fully-convolutional network for semantic segmentation of 3D point clouds, and apply it to challenging real-world datasets of indoor and outdoor 3D environments. Experimental results show that the presented approach outperforms other recent deep network constructions in detailed analysis of large 3D scenes.

The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing. This paper presents a novel framework named Point Cloud Transformer(PCT) for point cloud learning. PCT is based on Transformer, which achieves huge success in natural language processing and displays great potential in image processing. It is inherently permutation invariant for processing a sequence of points, making it well-suited for point cloud learning. To better capture local context within the point cloud, we enhance input embedding with the support of farthest point sampling and nearest neighbor search. Extensive experiments demonstrate that the PCT achieves the state-of-the-art performance on shape classification, part segmentation, semantic segmentation and normal estimation tasks.

由于多路径干扰（MPI），飞行时间（TOF）摄像机受高水平的噪声和扭曲。虽然最近的研究表明，2D神经网络能够以先前的传统最先进的（SOTA）方法胜过去噪，但已经完成了基于学习的方法的研究，以便直接使用存在的3D信息在深度图像中。在本文中，我们提出了一种在3D空间中运行的迭代去噪方法，该方法旨在通过启用3D点卷积来校正视图方向校正点的位置来学习2.5D数据。由于标记的现实世界数据稀缺了这项任务，我们进一步培训我们的网络，并在未标记的真实世界数据上培训我们的网络，以解释现实世界统计数据。我们展示我们的方法能够在多个数据集中倾斜SOTA方法，包括两个现实世界数据集和本文介绍的新的大规模合成数据集。

3D网格的几何特征学习是计算机图形的核心，对于许多视觉应用非常重要。然而，由于缺乏所需的操作和/或其有效的实现，深度学习目前滞后于异构3D网格的层次建模。在本文中，我们提出了一系列模块化操作，以实现异构3D网格的有效几何深度学习。这些操作包括网格卷曲，（UN）池和高效的网格抽取。我们提供这些操作的开源实施，统称为\ Texit {Picasso}。 Picasso的网格抽取模块是GPU加速的模块，可以在飞行中加工一批用于深度学习的网格。我们（联合国）汇集操作在不同分辨率的网络层跨网络层计算新创建的神经元的功能。我们的网格卷曲包括FaceT2Vertex，Vertex2Facet和FaceT2Facet卷积，用于利用VMF混合物和重心插值来包含模糊建模。利用Picasso的模块化操作，我们贡献了一个新型的分层神经网络Picassonet-II，以了解3D网格的高度辨别特征。 Picassonet-II接受原始地理学和Mesh Facet的精细纹理作为输入功能，同时处理完整场景网格。我们的网络达到了各种基准的形状分析和场景的竞争性能。我们在github https://github.com/enyahermite/picasso发布Picasso和Picassonet-II。

Point cloud learning has lately attracted increasing attention due to its wide applications in many areas, such as computer vision, autonomous driving, and robotics. As a dominating technique in AI, deep learning has been successfully used to solve various 2D vision problems. However, deep learning on point clouds is still in its infancy due to the unique challenges faced by the processing of point clouds with deep neural networks. Recently, deep learning on point clouds has become even thriving, with numerous methods being proposed to address different problems in this area. To stimulate future research, this paper presents a comprehensive review of recent progress in deep learning methods for point clouds. It covers three major tasks, including 3D shape classification, 3D object detection and tracking, and 3D point cloud segmentation. It also presents comparative results on several publicly available datasets, together with insightful observations and inspiring future research directions.

Convolutional networks are the de-facto standard for analyzing spatio-temporal data such as images, videos, and 3D shapes. Whilst some of this data is naturally dense (e.g., photos), many other data sources are inherently sparse. Examples include 3D point clouds that were obtained using a LiDAR scanner or RGB-D camera. Standard "dense" implementations of convolutional networks are very inefficient when applied on such sparse data. We introduce new sparse convolutional operations that are designed to process spatially-sparse data more efficiently, and use them to develop spatially-sparse convolutional networks. We demonstrate the strong performance of the resulting models, called submanifold sparse convolutional networks (SSCNs), on two tasks involving semantic segmentation of 3D point clouds. In particular, our models outperform all prior state-of-the-art on the test set of a recent semantic segmentation competition.

Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessarily voluminous and causes issues. In this paper, we design a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input. Our network, named PointNet, provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Though simple, PointNet is highly efficient and effective. Empirically, it shows strong performance on par or even better than state of the art. Theoretically, we provide analysis towards understanding of what the network has learnt and why the network is robust with respect to input perturbation and corruption.

从3D点云数据学习迅速获得了势头，这是通过深度学习的成功和图像的增加的3D数据的可用性。在本文中，我们的目标是构建直接在源点云的表面上工作的各向异性卷积。这是具有挑战性的，因为缺乏在表面上的切向方向的全局坐标系。我们介绍一个名为Deltaconv的新卷积运算符，将几何运算符从外部计算结合起来，以便在点云上构建各向异性滤波器。因为这些运算符在标量和向量字段上定义，所以我们将网络分开到标量和矢量流，由运算符连接。矢量流使网络能够明确表示，评估和处理方向信息。我们的卷轴稳健且易于实施，并显示出与最先进的基准相比提高准确性，同时加快培训和推理。

对森林生物量股票的知识及其发展对于实施有效的气候变化缓解措施是重要的。需要研究驾驶AF的过程，重新砍伐和森林砍伐，是碳核算的先决条件。使用空机激光雷达的遥感可用于测量大规模植被生物量。我们呈现深度学习系统，用于预测木材体积，地上生物量（AGB），随后直接从3D LIDAR点云数据碳。我们设计了不同的神经网络架构进行点云回归，并在遥感数据上评估AGB估计从国家森林库存中的现场测量获得的遥感数据。我们对回归的Minkowski卷积神经网络的调整给出了最佳结果。与在Point云的基本统计中运营的最先进的方法相比，深度神经网络产生了明显更准确的木材体积，AGB和碳估计，我们希望这一发现对基于LIDAR的分析产生了强烈影响陆地生态系统动态。

基于简单的扩散层对空间通信非常有效的洞察力，我们对3D表面进行深度学习的新的通用方法。由此产生的网络是自动稳健的，以改变表面的分辨率和样品 - 一种对实际应用至关重要的基本属性。我们的网络可以在各种几何表示上离散化，例如三角网格或点云，甚至可以在一个表示上培训然后应用于另一个表示。我们优化扩散的空间支持，作为连续网络参数，从纯粹的本地到完全全球范围，从而消除手动选择邻域大小的负担。该方法中唯一的其他成分是在每个点处独立地施加的多层的Perceptron，以及用于支持方向滤波器的空间梯度特征。由此产生的网络简单，坚固，高效。这里，我们主要专注于三角网格表面，并且展示了各种任务的最先进的结果，包括表面分类，分割和非刚性对应。

由于缺乏连接性信息，对局部表面几何形状进行建模在3D点云的理解中具有挑战性。大多数先前的作品使用各种卷积操作模拟本地几何形状。我们观察到，卷积可以等效地分解为局部和全球成分的加权组合。通过这种观察，我们明确地将这两个组件解散了，以便可以增强局部的组件并促进局部表面几何形状的学习。具体而言，我们提出了Laplacian单元（LU），这是一个简单而有效的建筑单元，可以增强局部几何学的学习。广泛的实验表明，配备有LU的网络在典型的云理解任务上实现了竞争性或卓越的性能。此外，通过建立平均曲率流之间的连接，基于曲率的LU进行了进一步研究，以解释LU的自适应平滑和锐化效果。代码将可用。

卷积神经网络（CNNS）在2D计算机视觉中取得了很大的突破。然而，它们的不规则结构使得难以在网格上直接利用CNNS的潜力。细分表面提供分层多分辨率结构，其中闭合的2 - 歧管三角网格中的每个面正恰好邻近三个面。本文推出了这两种观察，介绍了具有环形细分序列连接的3D三角形网格的创新和多功能CNN框架。在2D图像中的网格面和像素之间进行类比允许我们呈现网状卷积操作者以聚合附近面的局部特征。通过利用面部街区，这种卷积可以支持标准的2D卷积网络概念，例如，可变内核大小，步幅和扩张。基于多分辨率层次结构，我们利用汇集层，将四个面均匀地合并成一个和上采样方法，该方法将一个面分为四个。因此，许多流行的2D CNN架构可以容易地适应处理3D网格。可以通过自我参数化来回收具有任意连接的网格，以使循环细分序列连接，使子变量是一般的方法。广泛的评估和各种应用展示了SubDIVNet的有效性和效率。

深度神经网络需要特定的层来处理点云，因为点的分散和不规则位置使我们无法使用卷积过滤器。在这里，我们介绍了复合层，该复合层是点云的新卷积操作员。我们的复合层的特殊性是，它在将点与其特征向量结合之前从点位置提取和压缩空间信息。与众所周知的点横向跨层相比，我们的复合层提供了额外的正则化，并确保了参数和参数数量方面的灵活性更大。为了展示设计灵活性，我们还定义了一个集合复合层，该复合层以非线性方式组合空间信息和特征，并且我们使用这些层来实现卷积和聚集的综合材料。我们训练我们的复合烯类进行分类，最引人注目的是无监督的异常检测。我们对合成和现实世界数据集的实验表明，在这两个任务中，我们的CompositeNets都优于表现要点，尽管具有更简单的体系结构，但取得了与KPCONV相似的结果。此外，我们的复合烯类基本上优于现有的解决方案，用于点云上的异常检测。

Raw point clouds data inevitably contains outliers or noise through acquisition from 3D sensors or reconstruction algorithms. In this paper, we present a novel endto-end network for robust point clouds processing, named PointASNL, which can deal with point clouds with noise effectively. The key component in our approach is the adaptive sampling (AS) module. It first re-weights the neighbors around the initial sampled points from farthest point sampling (FPS), and then adaptively adjusts the sampled points beyond the entire point cloud. Our AS module can not only benefit the feature learning of point clouds, but also ease the biased effect of outliers. To further capture the neighbor and long-range dependencies of the sampled point, we proposed a local-nonlocal (L-NL) module inspired by the nonlocal operation. Such L-NL module enables the learning process insensitive to noise. Extensive experiments verify the robustness and superiority of our approach in point clouds processing tasks regardless of synthesis data, indoor data, and outdoor data with or without noise. Specifically, PointASNL achieves state-of-theart robust performance for classification and segmentation tasks on all datasets, and significantly outperforms previous methods on real-world outdoor SemanticKITTI dataset with considerate noise. Our code is released through https: //github.com/yanx27/PointASNL.

Deep neural networks have enjoyed remarkable success for various vision tasks, however it remains challenging to apply CNNs to domains lacking a regular underlying structures such as 3D point clouds. Towards this we propose a novel convolutional architecture, termed Spi-derCNN, to efficiently extract geometric features from point clouds. Spi-derCNN is comprised of units called SpiderConv, which extend convolutional operations from regular grids to irregular point sets that can be embedded in R n , by parametrizing a family of convolutional filters. We design the filter as a product of a simple step function that captures local geodesic information and a Taylor polynomial that ensures the expressiveness. SpiderCNN inherits the multi-scale hierarchical architecture from classical CNNs, which allows it to extract semantic deep features. Experiments on ModelNet40[4] demonstrate that SpiderCNN achieves state-of-the-art accuracy 92.4% on standard benchmarks, and shows competitive performance on segmentation task.