Current 3D object detection methods are heavily influenced by 2D detectors. In order to leverage architectures in 2D detectors, they often convert 3D point clouds to regular grids (i.e., to voxel grids or to bird's eye view images), or rely on detection in 2D images to propose 3D boxes. Few works have attempted to directly detect objects in point clouds. In this work, we return to first principles to construct a 3D detection pipeline for point cloud data and as generic as possible. However, due to the sparse nature of the data -samples from 2D manifolds in 3D space -we face a major challenge when directly predicting bounding box parameters from scene points: a 3D object centroid can be far from any surface point thus hard to regress accurately in one step. To address the challenge, we propose VoteNet, an end-to-end 3D object detection network based on a synergy of deep point set networks and Hough voting. Our model achieves state-of-the-art 3D detection on two large datasets of real 3D scans, ScanNet and SUN RGB-D with a simple design, compact model size and high efficiency. Remarkably, VoteNet outperforms previous methods by using purely geometric information without relying on color images.

In this work, we study 3D object detection from RGB-D data in both indoor and outdoor scenes. While previous methods focus on images or 3D voxels, often obscuring natural 3D patterns and invariances of 3D data, we directly operate on raw point clouds by popping up RGB-D scans. However, a key challenge of this approach is how to efficiently localize objects in point clouds of large-scale scenes (region proposal). Instead of solely relying on 3D proposals, our method leverages both mature 2D object detectors and advanced 3D deep learning for object localization, achieving efficiency as well as high recall for even small objects. Benefited from learning directly in raw point clouds, our method is also able to precisely estimate 3D bounding boxes even under strong occlusion or with very sparse points. Evaluated on KITTI and SUN RGB-D 3D detection benchmarks, our method outperforms the state of the art by remarkable margins while having real-time capability. * Majority of the work done as an intern at Nuro, Inc. depth to point cloud 2D region (from CNN) to 3D frustum 3D box (from PointNet)

In this paper, we propose PointRCNN for 3D object detection from raw point cloud. The whole framework is composed of two stages: stage-1 for the bottom-up 3D proposal generation and stage-2 for refining proposals in the canonical coordinates to obtain the final detection results. Instead of generating proposals from RGB image or projecting point cloud to bird's view or voxels as previous methods do, our stage-1 sub-network directly generates a small number of high-quality 3D proposals from point cloud in a bottom-up manner via segmenting the point cloud of the whole scene into foreground points and background. The stage-2 sub-network transforms the pooled points of each proposal to canonical coordinates to learn better local spatial features, which is combined with global semantic features of each point learned in stage-1 for accurate box refinement and confidence prediction. Extensive experiments on the 3D detection benchmark of KITTI dataset show that our proposed architecture outperforms state-of-the-art methods with remarkable margins by using only point cloud as input. The code is available at https://github.com/sshaoshuai/PointRCNN.

We present a new two-stage 3D object detection framework, named sparse-to-dense 3D Object Detector (STD). The first stage is a bottom-up proposal generation network that uses raw point cloud as input to generate accurate proposals by seeding each point with a new spherical anchor. It achieves a high recall with less computation compared with prior works. Then, PointsPool is applied for generating proposal features by transforming their interior point features from sparse expression to compact representation, which saves even more computation time. In box prediction, which is the second stage, we implement a parallel intersection-over-union (IoU) branch to increase awareness of localization accuracy, resulting in further improved performance. We conduct experiments on KITTI dataset, and evaluate our method in terms of 3D object and Bird's Eye View (BEV) detection. Our method outperforms other stateof-the-arts by a large margin, especially on the hard set, with inference speed more than 10 FPS.

We introduce Similarity Group Proposal Network (SGPN), a simple and intuitive deep learning framework for 3D object instance segmentation on point clouds. SGPN uses a single network to predict point grouping proposals and a corresponding semantic class for each proposal, from which we can directly extract instance segmentation results. Important to the effectiveness of SGPN is its novel representation of 3D instance segmentation results in the form of a similarity matrix that indicates the similarity between each pair of points in embedded feature space, thus producing an accurate grouping proposal for each point. Experimental results on various 3D scenes show the effectiveness of our method on 3D instance segmentation, and we also evaluate the capability of SGPN to improve 3D object detection and semantic segmentation results. We also demonstrate its flexibility by seamlessly incorporating 2D CNN features into the framework to boost performance.

3D object detection from LiDAR point cloud is a challenging problem in 3D scene understanding and has many practical applications. In this paper, we extend our preliminary work PointRCNN to a novel and strong point-cloud-based 3D object detection framework, the part-aware and aggregation neural network (Part-A 2 net). The whole framework consists of the part-aware stage and the part-aggregation stage. Firstly, the part-aware stage for the first time fully utilizes free-of-charge part supervisions derived from 3D ground-truth boxes to simultaneously predict high quality 3D proposals and accurate intra-object part locations. The predicted intra-object part locations within the same proposal are grouped by our new-designed RoI-aware point cloud pooling module, which results in an effective representation to encode the geometry-specific features of each 3D proposal. Then the part-aggregation stage learns to re-score the box and refine the box location by exploring the spatial relationship of the pooled intra-object part locations. Extensive experiments are conducted to demonstrate the performance improvements from each component of our proposed framework. Our Part-A 2 net outperforms all existing 3D detection methods and achieves new state-of-the-art on KITTI 3D object detection dataset by utilizing only the LiDAR point cloud data. Code is available at https://github.com/sshaoshuai/PointCloudDet3D.

捕获不规则点云的局部和全局特征对于3D对象检测（3OD）至关重要。但是，主流3D探测器，例如，投票机及其变体，要么放弃池操作过程中的大量本地功能，要么忽略整个场景中的许多全球功能。本文探讨了新的模块，以同时学习积极服务3OD的场景点云的局部全球特征。为此，我们通过同时局部全球特征学习（称为3DLG-detector）提出了一个有效的3OD网络。 3DLG检测器有两个关键贡献。首先，它会开发一个动态点交互（DPI）模块，该模块可在合并过程中保留有效的本地特征。此外，DPI是可拆卸的，可以将其合并到现有的3OD网络中以提高其性能。其次，它开发了一个全局上下文聚合模块，以汇总编码器不同层的多尺度特征，以实现场景上下文意识。我们的方法在SUN RGB-D和扫描仪数据集的检测准确性和鲁棒性方面显示了13个竞争对手的进步。源代码将在出版物时提供。

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.

3D场景从点云层的理解对各种机器人应用起着重要作用。遗憾的是，目前的最先进的方法使用单独的神经网络进行对象检测或房间布局估计等不同任务。这种方案具有两个限制：1）存储和运行多个网络以用于不同任务的网络对于典型的机器人平台昂贵。 2）忽略单独输出的内在结构，潜在地侵犯。为此，我们使用点云输入提出了第一变压器架构，其同时预测3D对象和布局。与估计布局关键点或边缘的现有方法不同，我们将单独参数化为一组四边形。因此，所提出的架构被称为p（oint）q（UAD）-Transformer。除了新颖的四边形表示之外，我们提出了一种量身定制的物理约束损失功能，阻碍对象布局干扰。公共基准SCANNet上的定量和定性评估表明，所提出的PQ变换器成功地共同解析了3D对象和布局，以准实时（8.91 FPS）速率运行而无需效率为导向的优化。此外，新的物理限制损失可以改善强力基线，房间布局的F1分数明显促进了37.9％至57.9％。

We focus on the task of amodal 3D object detection in RGB-D images, which aims to produce a 3D bounding box of an object in metric form at its full extent. We introduce Deep Sliding Shapes, a 3D ConvNet formulation that takes a 3D volumetric scene from a RGB-D image as input and outputs 3D object bounding boxes. In our approach, we propose the first 3D Region Proposal Network (RPN) to learn objectness from geometric shapes and the first joint Object Recognition Network (ORN) to extract geometric features in 3D and color features in 2D. In particular, we handle objects of various sizes by training an amodal RPN at two different scales and an ORN to regress 3D bounding boxes. Experiments show that our algorithm outperforms the state-of-the-art by 13.8 in mAP and is 200× faster than the original Sliding Shapes. Source code and pre-trained models are available.

最近，机器人和增强现实中的有希望的应用引起了从点云中的3D对象检测引起了相当大的关注。在本文中，我们展示了FCAF3D - 一流的全卷积锚无室内3D对象检测方法。它是一种简单而有效的方法，使用点云的体素表示，并处理具有稀疏卷曲的体素。 FCAF3D可以通过单个完全卷积前馈通量来处理具有最小运行时的大规模场景。现有的3D对象检测方法在对象的几何形状上进行现有假设，我们认为它限制了它们的泛化能力。为了摆脱任何先前的假设，我们提出了一种以纯粹的数据驱动方式获得更好的结果的导向边界框的新颖参数化。该方法在Scannet V2（+4.5），Sun RGB-D（+3.5）和S3DIS（+20.5）数据集上实现了最先进的3D对象检测结果。代码和模型可在https://github.com/samsunglabs/fcaf3d中获得。

点云的语义场景重建是3D场景理解的必不可少的任务。此任务不仅需要识别场景中的每个实例，而且还需要根据部分观察到的点云恢复其几何形状。现有方法通常尝试基于基于检测的主链的不完整点云建议直接预测完整对象的占用值。但是，由于妨碍了各种检测到的假阳性对象建议以及对完整对象学习占用值的不完整点观察的歧义，因此该框架始终无法重建高保真网格。为了绕开障碍，我们提出了一个分离的实例网格重建（DIMR）框架，以了解有效的点场景。采用基于分割的主链来减少假阳性对象建议，这进一步使我们对识别与重建之间关系的探索有益。根据准确的建议，我们利用网状意识的潜在代码空间来解开形状完成和网格生成的过程，从而缓解了由不完整的点观测引起的歧义。此外，通过在测试时间访问CAD型号池，我们的模型也可以通过在没有额外训练的情况下执行网格检索来改善重建质量。我们用多个指标彻底评估了重建的网格质量，并证明了我们在具有挑战性的扫描仪数据集上的优越性。代码可在\ url {https://github.com/ashawkey/dimr}上获得。

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.

变压器在自然语言处理中的成功最近引起了计算机视觉领域的关注。由于能够学习长期依赖性，变压器已被用作广泛使用的卷积运算符的替代品。事实证明，这种替代者在许多任务中都取得了成功，其中几种最先进的方法依靠变压器来更好地学习。在计算机视觉中，3D字段还见证了使用变压器来增加3D卷积神经网络和多层感知器网络的增加。尽管许多调查都集中在视力中的变压器上，但由于与2D视觉相比，由于数据表示和处理的差异，3D视觉需要特别注意。在这项工作中，我们介绍了针对不同3D视觉任务的100多种变压器方法的系统和彻底审查，包括分类，细分，检测，完成，姿势估计等。我们在3D Vision中讨论了变形金刚的设计，该设计使其可以使用各种3D表示形式处理数据。对于每个应用程序，我们强调了基于变压器的方法的关键属性和贡献。为了评估这些方法的竞争力，我们将它们的性能与12个3D基准测试的常见非转化方法进行了比较。我们通过讨论3D视觉中变压器的不同开放方向和挑战来结束调查。除了提出的论文外，我们的目标是频繁更新最新的相关论文及其相应的实现：https：//github.com/lahoud/3d-vision-transformers。

现有的基于深度学习的3D对象检测器通常依赖于单个对象的外观，并且不明确注意场景的丰富上下文信息。在这项工作中，我们为3D对象检测（CMR3D）框架提出了上下文化的多阶段完善，该框架将3D场景作为输入，并努力在多个级别上明确整合场景的有用上下文信息，以预测一组对象界限盒以及它们相应的语义标签。为此，我们建议利用一个上下文增强网络，该网络在不同级别的粒度级别上捕获上下文信息，然后是多阶段修补模块，以逐步完善框位置和类预测。大规模ScannETV2基准测试的广泛实验揭示了我们提出的方法的好处，从而使基线的绝对提高了2.0％。除3D对象检测外，我们还研究了CMR3D框架在3D对象计数问题上的有效性。我们的源代码将公开发布。

当前的3D分割方法很大程度上依赖于大规模的点状数据集，众所周知，这些数据集众所周知。很少有尝试规避需要每点注释的需求。在这项工作中，我们研究了弱监督的3D语义实例分割。关键的想法是利用3D边界框标签，更容易，更快地注释。确实，我们表明只有仅使用边界框标签训练密集的分割模型。在我们方法的核心上，\ name {}是一个深层模型，灵感来自经典的霍夫投票，直接投票赞成边界框参数，并且是专门针对边界盒票的专门定制的群集方法。这超出了常用的中心票，这不会完全利用边界框注释。在扫描仪测试中，我们弱监督的模型在其他弱监督的方法中获得了领先的性能（+18 MAP@50）。值得注意的是，它还达到了当前完全监督模型的50分数的地图的97％。为了进一步说明我们的工作的实用性，我们在最近发布的Arkitscenes数据集中训练Box2mask，该数据集仅使用3D边界框注释，并首次显示引人注目的3D实例细分掩码。

3D对象检测通过将点云作为唯一的输入来取得了显着的进展。但是，点云通常遭受不完整的几何结构和缺乏语义信息，这使得检测器难以准确地对检测到的对象进行分类。在这项工作中，我们专注于如何有效利用来自图像的对象级信息来提高基于点的3D检测器的性能。我们提出DEMF，这是一种简单而有效的方法，将图像信息融合到点特征中。给定一组点特征和图像特征图，DEMF通过将3D点的投影2D位置作为参考来自适应地汇总图像特征。我们在挑战性的Sun RGB-D数据集上评估了我们的方法，从而提高了最新的结果（+2.1 map@0.25和+2.3map@0.5）。代码可从https://github.com/haoy945/demf获得。

We present a novel and high-performance 3D object detection framework, named PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds. Our proposed method deeply integrates both 3D voxel Convolutional Neural Network (CNN) and PointNet-based set abstraction to learn more discriminative point cloud features. It takes advantages of efficient learning and high-quality proposals of the 3D voxel CNN and the flexible receptive fields of the PointNet-based networks. Specifically, the proposed framework summarizes the 3D scene with a 3D voxel CNN into a small set of keypoints via a novel voxel set abstraction module to save follow-up computations and also to encode representative scene features. Given the highquality 3D proposals generated by the voxel CNN, the RoIgrid pooling is proposed to abstract proposal-specific features from the keypoints to the RoI-grid points via keypoint set abstraction with multiple receptive fields. Compared with conventional pooling operations, the RoI-grid feature points encode much richer context information for accurately estimating object confidences and locations. Extensive experiments on both the KITTI dataset and the Waymo Open dataset show that our proposed PV-RCNN surpasses state-of-the-art 3D detection methods with remarkable margins by using only point clouds. Code is available at https://github.com/open-mmlab/OpenPCDet.

旋转阶段性最近已成为3D深度学习社区中强烈期望的财产。然而，大多数现有的方法都集中在对全局输入旋转的模棱两可，同时忽略了旋转对称性具有自己的空间支持的事实。具体而言，我们考虑3D场景中的对象检测问题，在该场景中，对象边界框在对象姿势上应具有等效性，而与场景运动无关。这表明我们称之为对象级旋转模棱两可的新的所需属性。为了将对象级旋转等效率纳入3D对象探测器，我们需要一种机制来提取具有本地对象级空间支持的模棱两可的功能，同时能够对跨对象上下文信息进行建模。为此，我们提出了具有旋转模棱两可悬架设计的均衡对象检测网络（EON），以实现对象级的等效性。 EON可以应用于现代点云对象检测器，例如votenet和pointrcnn，使它们能够利用场景尺度输入中的对象旋转对称性。我们在室内场景和自动驾驶数据集上进行的实验表明，通过将我们的EON设计插入现有的最新3D对象检测器来获得重大改进。

我们介绍了一种方法，例如针对3D点云的提案生成。现有技术通常直接在单个进料前进的步骤中回归建议，从而导致估计不准确。我们表明，这是一个关键的瓶颈，并提出了一种基于迭代双边滤波的方法。遵循双边滤波的精神，我们考虑了每个点的深度嵌入以及它们在3D空间中的位置。我们通过合成实验表明，在为给定的兴趣点生成实例建议时，我们的方法会带来巨大的改进。我们进一步验证了我们在挑战性扫描基准测试中的方法，从而在自上而下的方法的子类别中实现了最佳实例分割性能。