In many robotics and VR/AR applications, 3D-videos are readily-available sources of input (a continuous sequence of depth images, or LIDAR scans). However, these 3D-videos are processed frame-by-frame either through 2D convnets or 3D perception algorithms in many cases. In this work, we propose 4-dimensional convolutional neural networks for spatio-temporal perception that can directly process such 3D-videos using high-dimensional convolutions. For this, we adopt sparse tensors [8, 9] and propose the generalized sparse convolution which encompasses all discrete convolutions. To implement the generalized sparse convolution, we create an open-source auto-differentiation library for sparse tensors that provides extensive functions for highdimensional convolutional neural networks. 1 We create 4D spatio-temporal convolutional neural networks using the library and validate them on various 3D semantic segmentation benchmarks and proposed 4D datasets for 3D-video perception. To overcome challenges in the high-dimensional 4D space, we propose the hybrid kernel, a special case of the generalized sparse convolution, and the trilateral-stationary conditional random field that enforces spatio-temporal consistency in the 7D space-time-chroma space. Experimentally, we show that convolutional neural networks with only generalized sparse convolutions can outperform 2D or 2D-3D hybrid methods by a large margin. 2 Also, we show that on 3D-videos, 4D spatio-temporal convolutional neural networks are robust to noise, outperform 3D convolutional neural networks and are faster than the 3D counterpart in some cases.

对于许多3D视觉任务，包括对象检测，分割，注册和3D输入的各种感知任务，这一点是普遍的。然而，由于3D数据的稀疏性和不规则性，定制3D运算符或网络设计一直是3D研究的主要焦点，而参数的网络或参数的功效的大小被忽略了。在这项工作中，我们对空间稀疏3D卷积网络的重量稀疏性进行了第一综合研究，并提出了一种用于语义分割和实例分割的紧凑的权重稀疏和空间稀疏的3D Conver（WS ^ 3-Tromet）。我们采用各种网络修剪策略来查找紧凑的网络，并展示我们的WS ^ 3-TRMYNET在数值较少数量的参数（1/100压缩速率）中实现了最小的性能（2.15％掉落）。最后，我们系统地分析了WS ^ 3-Tromnet的压缩模式，并在我们的压缩网络中显示了有趣的新出现的稀疏模式，以进一步加速推断。

Standard convolutional neural networks assume a grid structured input is available and exploit discrete convolutions as their fundamental building blocks. This limits their applicability to many real-world applications. In this paper we propose Parametric Continuous Convolution, a new learnable operator that operates over non-grid structured data. The key idea is to exploit parameterized kernel functions that span the full continuous vector space. This generalization allows us to learn over arbitrary data structures as long as their support relationship is computable. Our experiments show significant improvement over the state-ofthe-art in point cloud segmentation of indoor and outdoor scenes, and lidar motion estimation of driving scenes.

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.

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 propose a novel deep learning-based framework to tackle the challenge of semantic segmentation of largescale point clouds of millions of points. We argue that the organization of 3D point clouds can be efficiently captured by a structure called superpoint graph (SPG), derived from a partition of the scanned scene into geometrically homogeneous elements. SPGs offer a compact yet rich representation of contextual relationships between object parts, which is then exploited by a graph convolutional network. Our framework sets a new state of the art for segmenting outdoor LiDAR scans (+11.9 and +8.8 mIoU points for both Semantic3D test sets), as well as indoor scans (+12.4 mIoU points for the S3DIS dataset).

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.

隐式3D表示的最新进展，即神经辐射场（NERFS），以可区分的方式使准确且具有逼真的3D重建成为可能。这种新的表示可以有效地以一种紧凑的格式传达数百个高分辨率图像的信息，并允许对新观点的逼真综合。在这项工作中，使用NERF的变体称为全体氧，我们为感知任务创建了第一个大规模隐式表示数据集，称为Fustection，该数据集由两个部分组成，这些部分既包含以对象为中心和场景为中心的扫描，用于分类和分段， 。它显示了原始数据集的显着内存压缩率（96.4 \％），同时以统一形式包含2D和3D信息。我们构建了直接作为输入这种隐式格式的分类和分割模型，并提出了一种新颖的增强技术，以避免在图像的背景上过度拟合。代码和数据可在https://postech-cvlab.github.io/perfception中公开获得。

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。

Extracting geometric features from 3D scans or point clouds is the first step in applications such as registration, reconstruction, and tracking. State-of-the-art methods require computing low-level features as input or extracting patch-based features with limited receptive field.In this work, we present fully-convolutional geometric features, computed in a single pass by a 3D fully-convolutional network. We also present new metric learning losses that dramatically improve performance. Fully-convolutional geometric features are compact, capture broad spatial context, and scale to large scenes. We experimentally validate our approach on both indoor and outdoor datasets. Fullyconvolutional geometric features achieve state-of-the-art accuracy without requiring prepossessing, are compact (32 dimensions), and are 290 times faster than the most accurate prior method.

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.

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.

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.

我们介绍了PointConvormer，这是一个基于点云的深神经网络体系结构的新颖构建块。受到概括理论的启发，PointConvormer结合了点卷积的思想，其中滤波器权重仅基于相对位置，而变形金刚则利用了基于功能的注意力。在PointConvormer中，附近点之间的特征差异是重量重量卷积权重的指标。因此，我们从点卷积操作中保留了不变，而注意力被用来选择附近的相关点进行卷积。为了验证PointConvormer的有效性，我们在点云上进行了语义分割和场景流估计任务，其中包括扫描仪，Semantickitti，FlyingThings3D和Kitti。我们的结果表明，PointConvormer具有经典的卷积，常规变压器和Voxelized稀疏卷积方法的表现，具有较小，更高效的网络。可视化表明，PointConvormer的性能类似于在平面表面上的卷积，而邻域选择效果在物体边界上更强，表明它具有两全其美。

We present OctNet, a representation for deep learning with sparse 3D data. In contrast to existing models, our representation enables 3D convolutional networks which are both deep and high resolution. Towards this goal, we exploit the sparsity in the input data to hierarchically partition the space using a set of unbalanced octrees where each leaf node stores a pooled feature representation. This allows to focus memory allocation and computation to the relevant dense regions and enables deeper networks without compromising resolution. We demonstrate the utility of our OctNet representation by analyzing the impact of resolution on several 3D tasks including 3D object classification, orientation estimation and point cloud labeling.

We present a network architecture for processing point clouds that directly operates on a collection of points represented as a sparse set of samples in a high-dimensional lattice. Naïvely applying convolutions on this lattice scales poorly, both in terms of memory and computational cost, as the size of the lattice increases. Instead, our network uses sparse bilateral convolutional layers as building blocks. These layers maintain efficiency by using indexing structures to apply convolutions only on occupied parts of the lattice, and allow flexible specifications of the lattice structure enabling hierarchical and spatially-aware feature learning, as well as joint 2D-3D reasoning. Both point-based and image-based representations can be easily incorporated in a network with such layers and the resulting model can be trained in an end-to-end manner. We present results on 3D segmentation tasks where our approach outperforms existing state-of-the-art techniques.

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.

最近神经网络的成功使得能够更好地解释3D点云，但是处理大规模的3D场景仍然是一个具有挑战性的问题。大多数电流方法将大型场景划分为小区，并将当地预测组合在一起。然而，该方案不可避免地涉及预处理和后处理的附加阶段，并且由于局部视角下的预测也可能降低最终输出。本文介绍了由新的轻质自我关注层组成的快速点变压器。我们的方法编码连续的3D坐标，基于体素散列的架构提高了计算效率。所提出的方法用3D语义分割和3D检测进行了说明。我们的方法的准确性对基于最佳的体素的方法具有竞争力，我们的网络达到了比最先进的点变压器更快的推理时间速度更快的136倍，具有合理的准确性权衡。

自动驾驶汽车广泛使用屋顶旋转的LIDAR传感器，推动了3D点序列实时处理的需求。但是，大多数激光雷达语义细分数据集和算法将这些收购分为$ 360^\ circ $框架，从而导致收购潜伏期与现实的实时应用程序和评估不符。我们通过两个关键贡献来解决这个问题。首先，我们介绍Helixnet，这是一个10亿美元的点数据集，具有细粒度的标签，时间戳和传感器旋转信息，可以准确评估分割算法的实时准备就绪。其次，我们提出了helix4d，这是一种专门设计用于旋转激光雷达点序列的紧凑而有效的时空变压器结构。 Helix4D在采集切片上运行，对应于传感器的全部旋转的一部分，从而大大降低了总延迟。我们介绍了Helixnet和Semantickitti上几种最先进模型的性能和实时准备的广泛基准。 Helix4D与最佳的分割算法达到准确性，而在延迟和型号$ 50 \ times $中，降低了$ 5 \ times $。代码和数据可在以下网址获得：https：//romainloiseau.fr/helixnet

In this paper, we address semantic segmentation of road-objects from 3D LiDAR point clouds. In particular, we wish to detect and categorize instances of interest, such as cars, pedestrians and cyclists. We formulate this problem as a pointwise classification problem, and propose an end-to-end pipeline called SqueezeSeg based on convolutional neural networks (CNN): the CNN takes a transformed LiDAR point cloud as input and directly outputs a point-wise label map, which is then refined by a conditional random field (CRF) implemented as a recurrent layer. Instance-level labels are then obtained by conventional clustering algorithms. Our CNN model is trained on LiDAR point clouds from the KITTI [1] dataset, and our point-wise segmentation labels are derived from 3D bounding boxes from KITTI. To obtain extra training data, we built a LiDAR simulator into Grand Theft Auto V (GTA-V), a popular video game, to synthesize large amounts of realistic training data. Our experiments show that SqueezeSeg achieves high accuracy with astonishingly fast and stable runtime (8.7 ± 0.5 ms per frame), highly desirable for autonomous driving applications. Furthermore, additionally training on synthesized data boosts validation accuracy on real-world data. Our source code and synthesized data will be open-sourced.