With advances in deep learning model training strategies, the training of Point cloud classification methods is significantly improving. For example, PointNeXt, which adopts prominent training techniques and InvResNet layers into PointNet++, achieves over 7% improvement on the real-world ScanObjectNN dataset. However, most of these models use point coordinates features of neighborhood points mapped to higher dimensional space while ignoring the neighborhood point features computed before feeding to the network layers. In this paper, we revisit the PointNeXt model to study the usage and benefit of such neighborhood point features. We train and evaluate PointNeXt on ModelNet40 (synthetic), ScanObjectNN (real-world), and a recent large-scale, real-world grocery dataset, i.e., 3DGrocery100. In addition, we provide an additional inference strategy of weight averaging the top two checkpoints of PointNeXt to improve classification accuracy. Together with the abovementioned ideas, we gain 0.5%, 1%, 4.8%, 3.4%, and 1.6% overall accuracy on the PointNeXt model with real-world datasets, ScanObjectNN (hardest variant), 3DGrocery100's Apple10, Fruits, Vegetables, and Packages subsets, respectively. We also achieve a comparable 0.2% accuracy gain on ModelNet40.

标准空间卷积假设具有常规邻域结构的输入数据。现有方法通常通过修复常规“视图”来概括对不规则点云域的卷积。固定的邻域大小，卷积内核大小对于每个点保持不变。然而，由于点云不是像图像的结构，所以固定邻权给出了不幸的感应偏压。我们提出了一个名为digress图卷积（diffconv）的新图表卷积，不依赖常规视图。DiffConv在空间 - 变化和密度扩张的邻域上操作，其进一步由学习屏蔽的注意机制进行了进一步调整。我们在ModelNet40点云分类基准测试中验证了我们的模型，获得最先进的性能和更稳健的噪声，以及更快的推广速度。

Few prior works study deep learning on point sets. PointNet [20] is a pioneer in this direction. However, by design PointNet does not capture local structures induced by the metric space points live in, limiting its ability to recognize fine-grained patterns and generalizability to complex scenes. In this work, we introduce a hierarchical neural network that applies PointNet recursively on a nested partitioning of the input point set. By exploiting metric space distances, our network is able to learn local features with increasing contextual scales. With further observation that point sets are usually sampled with varying densities, which results in greatly decreased performance for networks trained on uniform densities, we propose novel set learning layers to adaptively combine features from multiple scales. Experiments show that our network called PointNet++ is able to learn deep point set features efficiently and robustly. In particular, results significantly better than state-of-the-art have been obtained on challenging benchmarks of 3D point clouds.

有效处理3D数据一直是一个挑战。大规模点云上的空间操作以稀疏数据存储，需要额外的成本。由于变形金刚的成功吸引，研究人员正在使用多头关注视力任务。但是，变压器中的注意力计算在输入数量和点云等集合的空间直觉中具有二次复杂性。我们重新设计了这项工作中的“变压器”，并将它们纳入形状分类以及部分和场景细分的层次结构框架中。我们建议我们的当地注意力单元，该单元捕获了空间社区的特征。我们还通过利用每次迭代的采样和分组来计算有效且动态的全局交叉注意。最后，为了减轻点云的非异质性，我们提出了一个有效的多尺度令牌化（MST），该标记（MST）提取了尺度不变的令牌以供注意操作。所提出的分层模型以平均准确性实现最新的形状分类，并以先前的分割方法的相同，同时需要更少的计算。我们提出的体系结构预测分割标签的标签约为以前最有效方法的延迟和参数计数的一半，具有可比的性能。该代码可从https://github.com/yigewang-whu/cloudattention获得。

学习3D点云的新表示形式是3D视觉中的一个活跃研究领域，因为订单不变的点云结构仍然对神经网络体系结构的设计构成挑战。最近的作品探索了学习全球或本地功能或两者兼而有之，但是均未通过分析点的局部方向分布来捕获上下文形状信息的早期方法。在本文中，我们利用点附近的点方向分布，以获取点云的表现力局部邻里表示。我们通过将给定点的球形邻域分为预定义的锥体来实现这一目标，并将每个体积内部的统计数据用作点特征。这样，本地贴片不仅可以由所选点的最近邻居表示，还可以考虑沿该点周围多个方向定义的点密度分布。然后，我们能够构建涉及依赖MLP（多层感知器）层的Odfblock的方向分布函数（ODF）神经网络。新的ODFNET模型可实现ModelNet40和ScanObjectNN数据集的对象分类的最新精度，并在Shapenet S3DIS数据集上进行分割。

我们提出了一种基于注意力的新型机制，可以学习用于点云处理任务的增强点特征，例如分类和分割。与先前的作品不同，该作品经过培训以优化预选的一组注意点的权重，我们的方法学会了找到最佳的注意点，以最大程度地提高特定任务的性能，例如点云分类。重要的是，我们主张使用单个注意点来促进语义理解在点特征学习中。具体而言，我们制定了一种新的简单卷积，该卷积结合了输入点及其相应学习的注意点或膝盖的卷积特征。我们的注意机制可以轻松地纳入最新的点云分类和分割网络中。对诸如ModelNet40，ShapenetPart和S3DIS之类的常见基准测试的广泛实验都表明，我们的支持LAP的网络始终优于各自的原始网络，以及其他竞争性替代方案，这些替代方案在我们的膝盖下采用了多个注意力框架。

学习地区内部背景和区域间关系是加强点云分析的特征表示的两项有效策略。但是，在现有方法中没有完全强调的统一点云表示的两种策略。为此，我们提出了一种名为点关系感知网络（PRA-NET）的小说框架，其由区域内结构学习（ISL）模块和区域间关系学习（IRL）模块组成。ISL模块可以通过可差的区域分区方案和基于代表的基于点的策略自适应和有效地将本地结构信息动态地集成到点特征中，而IRL模块可自适应和有效地捕获区域间关系。在涵盖形状分类，关键点估计和部分分割的几个3D基准测试中的广泛实验已经验证了PRA-Net的有效性和泛化能力。代码将在https://github.com/xiwuchen/pra-net上获得。

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.

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.

Point cloud analysis is very challenging, as the shape implied in irregular points is difficult to capture. In this paper, we propose RS-CNN, namely, Relation-Shape Convolutional Neural Network, which extends regular grid CNN to irregular configuration for point cloud analysis.The key to RS-CNN is learning from relation, i.e., the geometric topology constraint among points. Specifically, the convolutional weight for local point set is forced to learn a high-level relation expression from predefined geometric priors, between a sampled point from this point set and the others. In this way, an inductive local representation with explicit reasoning about the spatial layout of points can be obtained, which leads to much shape awareness and robustness. With this convolution as a basic operator, RS-CNN, a hierarchical architecture can be developed to achieve contextual shape-aware learning for point cloud analysis. Extensive experiments on challenging benchmarks across three tasks verify RS-CNN achieves the state of the arts.

借助深度学习范式，许多点云网络已经发明了用于视觉分析。然而，由于点云数据的给定信息尚未完全利用，因此对这些网络的发展存在很大的潜力。为了提高现有网络在分析点云数据中的有效性，我们提出了一个即插即用模块，PNP-3D，旨在通过涉及更多来自显式3D空间的本地背景和全球双线性响应来改进基本点云特征表示隐含的功能空间。为了彻底评估我们的方法，我们对三个标准点云分析任务进行实验，包括分类，语义分割和对象检测，在那里我们从每个任务中选择三个最先进的网络进行评估。作为即插即用模块，PNP-3D可以显着提高已建立的网络的性能。除了在四个广泛使用的点云基准测试中实现最先进的结果，我们还提供了全面的消融研究和可视化，以展示我们的方法的优势。代码将在https://github.com/shiqiu0419/pnp-3d上获得。

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.

Downsampling and feature extraction are essential procedures for 3D point cloud understanding. Existing methods are limited by the inconsistent point densities of different parts in the point cloud. In this work, we analyze the limitation of the downsampling stage and propose the pre-abstraction group-wise window-normalization module. In particular, the window-normalization method is leveraged to unify the point densities in different parts. Furthermore, the group-wise strategy is proposed to obtain multi-type features, including texture and spatial information. We also propose the pre-abstraction module to balance local and global features. Extensive experiments show that our module performs better on several tasks. In segmentation tasks on S3DIS (Area 5), the proposed module performs better on small object recognition, and the results have more precise boundaries than others. The recognition of the sofa and the column is improved from 69.2% to 84.4% and from 42.7% to 48.7%, respectively. The benchmarks are improved from 71.7%/77.6%/91.9% (mIoU/mAcc/OA) to 72.2%/78.2%/91.4%. The accuracies of 6-fold cross-validation on S3DIS are 77.6%/85.8%/91.7%. It outperforms the best model PointNeXt-XL (74.9%/83.0%/90.3%) by 2.7% on mIoU and achieves state-of-the-art performance. The code and models are available at https://github.com/DBDXSS/Window-Normalization.git.

随着激光雷达传感器和3D视觉摄像头的扩散，3D点云分析近年来引起了重大关注。经过先驱工作点的成功后，基于深度学习的方法越来越多地应用于各种任务，包括3D点云分段和3D对象分类。在本文中，我们提出了一种新颖的3D点云学习网络，通过选择性地执行具有动态池的邻域特征聚合和注意机制来提出作为动态点特征聚合网络（DPFA-NET）。 DPFA-Net有两个可用于三维云的语义分割和分类的变体。作为DPFA-NET的核心模块，我们提出了一个特征聚合层，其中每个点的动态邻域的特征通过自我注意机制聚合。与其他分割模型相比，来自固定邻域的聚合特征，我们的方法可以在不同层中聚合来自不同邻居的特征，在不同层中为查询点提供更具选择性和更广泛的视图，并更多地关注本地邻域中的相关特征。此外，为了进一步提高所提出的语义分割模型的性能，我们提出了两种新方法，即两级BF-Net和BF-Rengralization来利用背景前台信息。实验结果表明，所提出的DPFA-Net在S3DIS数据集上实现了最先进的整体精度分数，在S3DIS数据集上进行了语义分割，并在不同的语义分割，部分分割和3D对象分类中提供始终如一的令人满意的性能。与其他方法相比，它也在计算上更有效。

This paper presents PointWeb, a new approach to extract contextual features from local neighborhood in a point cloud. Unlike previous work, we densely connect each point with every other in a local neighborhood, aiming to specify feature of each point based on the local region characteristics for better representing the region. A novel module, namely Adaptive Feature Adjustment (AFA) module, is presented to find the interaction between points. For each local region, an impact map carrying element-wise impact between point pairs is applied to the feature difference map. Each feature is then pulled or pushed by other features in the same region according to the adaptively learned impact indicators. The adjusted features are well encoded with region information, and thus benefit the point cloud recognition tasks, such as point cloud segmentation and classification. Experimental results show that our model outperforms the state-of-the-arts on both semantic segmentation and shape classification datasets.

最近，深度神经网络在3D点云分类方面取得了显着成就。然而，现有的分类方法主要在理想化点云上实施，并在非理想情况下遭受重大降解的每种性能。为了处理该Prob-LEM，提出了一个名为双邻居深度融合网络（DNDFN）的特征表示学习方法，以用作非理想点云分类任务的改进点云编码器。 DNDFN利用称为TN学习的培训邻域学习方法来捕获全局关键邻域。然后，全球邻居与当地邻居融合，以帮助网络实现更强大的推理能力。此外，提出了一个信息传输卷积（IT-CONV）为DNDFN学习点对对之间的边缘信息，并使特征传输过程受益。 IT-CONV中的信息传输类似于图中的信息的传播，其使DNDF​​N更靠近人工理工模式。关于现有基准的广泛实验尤其是非理想的数据集验证了DNDFN和DNDFN实现了最先进的效果。

场景流程描绘了3D场景的动态，这对于传统上，从诸如自主驾驶，机器人导航，AR / VR等的各种应用来说至关重要。从密集/常规RGB视频帧估计场景流。随着深度感测技术的发展，通过点云可获得精确的3D测量，这在3D场景流中引发了新的研究。然而，由于典型点云采样模式中的稀缺性和不规则性，从点云中提取场景流量仍然具有挑战性。与不规则采样相关的一个主要问题被识别为点设置抽象/特征提取期间的随机性 - 许多流程估计场景中的基本进程。因此，提出了一种注意力（SA ^ 2）层的新型空间抽象，以减轻不稳定的抽象问题。此外，提出了一种注意力（TA ^ 2）层的时间抽象来纠正时间域中的注意力，导致运动中的运动缩放在更大范围内。广泛的分析和实验验证了我们方法的动机和显着性能收益，与空间 - 时间注意（Festa）称为流量估计，与场景流估计的几个最先进的基准相比。

通过当地地区的点特征聚合来捕获的细粒度几何是对象识别和场景理解在点云中的关键。然而，现有的卓越点云骨架通常包含最大/平均池用于局部特征聚集，这在很大程度上忽略了点的位置分布，导致细粒结构组装不足。为了缓解这一瓶颈，我们提出了一个有效的替代品，可以使用新颖的图形表示明确地模拟了本地点之间的空间关系，并以位置自适应方式聚合特征，从而实现位置敏感的表示聚合特征。具体而言，Papooling分别由两个关键步骤，图形结构和特征聚合组成，分别负责构造与将中心点连接的边缘与本地区域中的每个相邻点连接的曲线图组成，以将它们的相对位置信息映射到通道 - 明智的细心权重，以及基于通过图形卷积网络（GCN）的生成权重自适应地聚合局部点特征。 Papooling简单而且有效，并且足够灵活，可以随时为PointNet ++和DGCNN等不同的流行律源，作为即插即说运算符。关于各种任务的广泛实验，从3D形状分类，部分分段对场景分割良好的表明，伪装可以显着提高预测准确性，而具有最小的额外计算开销。代码将被释放。

通过深度传感器捕获的点云通常被噪音污染，阻碍了进一步的分析和应用。在本文中，我们强调了点分布均匀性对下游任务的重要性。我们证明了现有基于梯度的DeNoiser产生的点云尽管取得了有希望的定量结果，但仍缺乏统一性。为此，我们提出了GPCD ++，这是一种基于梯度的DeNoiser，其超轻质网络名为UNINET，以解决均匀性。与以前的最先进方法相比，我们的方法不仅会产生竞争性甚至更好地降解结果，而且还显着改善了统一性，这在很大程度上使诸如表面重建之类的应用受益。