本研究通过基于稀疏的张量处理(STP)的Voxelized PCG的多尺度表示,通过稀疏的张解器处理(STP)进行了一种统一点云几何形状(PCG)压缩方法。应用STP显着降低了复杂性,因为它只执行以最可能的积极占用体素(MP-POV)为中心的卷曲。并且多尺度代表有助于我们逐步压缩规模明智的MP-POV。总压缩效率高度取决于每个MP-POV的占用概率的近似精度。因此,我们设计基于稀疏的卷积的神经网络(Sparsecnn),包括稀疏卷曲和体素重新采样以广泛利用前沿。然后,我们开发基于SPARSECNN的占用概率近似(SOPA)模型,以估计在单阶段的方式中仅在逐步使用自回归邻居之前或以多阶段使用的横级或以多级的方式估计占用概率。此外,我们还建议基于SPARSECNN的本地邻居嵌入(SLNE),以表征当地空间变化作为改进SOPA的特征属性。我们的统一方法显示了在与MPEG G-PCC相比的各种数据集中,包括致密PCG(8iVFB,OWLII)和稀疏LIDAR PCG(KITTI,FORD)的各种数据集中的无损压缩模式中的最先进的性能和其他基于学习的压缩方案。此外,所提出的方法由于跨越所有尺度的模型共享而引起的轻量级复杂性,并且由于模型共享。我们使所有材料可在HTTPS://github.com/njuvision/sparsepcgc上公开访问可重复的研究。
translated by 谷歌翻译
尽管多尺度稀疏张量的卷积表示表明其较高的效率,可以准确地模拟密集对象点云的几何形状分量压缩的占用概率,但其代表稀疏的LIDAR点云几何形状(PCG)的能力在很大程度上受到限制。这是因为1)卷积的固定接受场不能很好地表征极其分布的稀疏点点; 2)经过固定权重的经过预定的卷积不足以动态捕获在输入条件下的信息。因此,这项工作暗示了邻里点的注意(NPA)来解决它们,在那里我们首先使用K最近的邻居(KNN)来构建自适应的当地社区。然后利用自我发明机制在该社区内动态汇总信息。将这种NPA设计为最佳利用跨尺度和相同相关性的NPA形式,以进行几何占用概率估计。与使用标准化G-PCC锚的锚相比,我们的方法为有损压缩提供了> 17%的BD率增长,并且使用Semantickitti和Ford数据集中流行的LIDAR点云的无损场景降低了> 14%的比特率。与使用注意力优化的OCTREE编码方法的最先进的(SOTA)解决方案相比,我们的方法平均需要减少分解运行时的分解时间要少得多,同时仍提出更好的压缩效率。
translated by 谷歌翻译
有效的点云压缩对于虚拟和混合现实,自动驾驶和文化遗产等应用至关重要。在本文中,我们为动态点云几何压缩提出了一个基于深度学习的框架间编码方案。我们提出了一种有损的几何压缩方案,该方案通过使用新的预测网络,使用先前的框架来预测当前帧的潜在表示。我们提出的网络利用稀疏的卷积使用层次多尺度3D功能学习来使用上一个帧编码当前帧。我们在目标坐标上采用卷积来将上一个帧的潜在表示为当前帧的降采样坐标,以预测当前帧的特征嵌入。我们的框架通过使用学习的概率分解熵模型来压缩预测功能的残差和实际特征。在接收器中,解码器层次结构通过逐步重新嵌入功能嵌入来重建当前框架。我们将我们的模型与基于最先进的视频点云压缩(V-PCC)和基于几何的点云压缩(G-PCC)方案进行了比较,该方案由Moving Picture Experts Group(MPEG)标准化。我们的方法实现了91%以上的BD率Bjontegaard三角洲率)降低了G-PCC,针对V-PCC框架内编码模式的BD率降低了62%以上,而对于V-PC。使用HEVC,基于PCC P框架的框架间编码模式。
translated by 谷歌翻译
为基于几何的点云压缩(G-PCC)标准开发了基于学习的自适应环滤波器,以减少属性压缩工件。提出的方法首先生成多个最可行的样品偏移(MPSO)作为潜在的压缩失真近似值,然后线性权重以减轻伪影。因此,我们将过滤后的重建驱动尽可能靠近未压缩的PCA。为此,我们设计了一个由两个连续的处理阶段组成的压缩工件还原网络(CARNET):MPSOS推导和MPSOS组合。 MPSOS派生使用两个流网络来模拟来自直接空间嵌入和频率依赖性嵌入的局部邻域变化,在该嵌入中,稀疏的卷积被利用可从细微和不规则分布的点中最佳汇总信息。 MPSOS组合由最小平方误量学指导,以进一步捕获输入PCAS的内容动力学,从而得出加权系数。 Carnet作为GPCC的环内过滤工具实现,其中这些线性加权系数被封装在比特斯流中,并以忽略不计的比特率开销。实验结果表明,对最新的GPCC的主观和客观性都显着改善。
translated by 谷歌翻译
点云压缩(PCC)是各种3-D应用程序的关键推动器,这是由于点云格式的通用性。理想情况下,3D点云努力描绘了连续的对象/场景表面。实际上,作为一组离散样本,点云是局部断开连接并稀疏分布的。这种稀疏的性质阻碍了在压缩点之间发现局部相关性的发现。通过分形维度的分析,我们提出了一种异质方法,并深入学习有损耗的点云几何压缩。在压缩输入的粗表示的基础层的顶部上,增强层的设计旨在应对具有挑战性的几何残差/详细信息。具体而言,应用基于点的网络将不稳定的本地详细信息转换为位于粗点云上的潜在特征。然后启动了在粗点云上运行的稀疏卷积神经网络。它利用粗糙几何形状的连续性/平滑度来压缩潜在特征,作为增强的位流,极大地使重建质量受益。当此位流不可用时,例如,由于数据包丢失,我们支持具有相同体系结构的跳过模式,该模式直接从粗点云中生成几何细节。对密度和稀疏点云的实验证明了我们的提案实现的最新压缩性能。我们的代码可在https://github.com/interdigitalinc/grasp-net上找到。
translated by 谷歌翻译
激光点云(LPC)的非均匀分布和极稀疏的性质给其高效压缩带来了重大挑战。本文提出了一个新颖的端到端,完全物质的深层框架,该框架将原始LPC编码为OCTREE结构,并分层分解OCTREE熵模型。所提出的框架利用层次的潜在变量作为侧面信息来封装兄弟姐妹和祖先依赖性,该依赖性为点云分布的建模提供了足够的上下文信息,同时启用了同一层中的Octree节点的并行编码和解码。此外,我们提出了一个用于压缩潜在变量的残留编码框架,该框架通过渐进的下采样探索了每一层的空间相关性,并用完全属于熵模型对相应的残差进行建模。此外,我们提出了剩余编码的软添加和减法,以提高网络灵活性。 LIDAR基准Semantickitti和MPEG指定数据集福特的综合实验结果表明,我们提出的框架在所有以前的LPC框架中都实现了最先进的性能。此外,我们的端到端,完全物质化的框架被实验证明是高平行和及时效率的,并且与以前的LPC压缩方法相比,与以前的最新方法相比,可以节省超过99.8%的解码时间。
translated by 谷歌翻译
Due to the diverse sparsity, high dimensionality, and large temporal variation of dynamic point clouds, it remains a challenge to design an efficient point cloud compression method. We propose to code the geometry of a given point cloud by learning a neural volumetric field. Instead of representing the entire point cloud using a single overfit network, we divide the entire space into small cubes and represent each non-empty cube by a neural network and an input latent code. The network is shared among all the cubes in a single frame or multiple frames, to exploit the spatial and temporal redundancy. The neural field representation of the point cloud includes the network parameters and all the latent codes, which are generated by using back-propagation over the network parameters and its input. By considering the entropy of the network parameters and the latent codes as well as the distortion between the original and reconstructed cubes in the loss function, we derive a rate-distortion (R-D) optimal representation. Experimental results show that the proposed coding scheme achieves superior R-D performances compared to the octree-based G-PCC, especially when applied to multiple frames of a point cloud video. The code is available at https://github.com/huzi96/NVFPCC/.
translated by 谷歌翻译
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.
translated by 谷歌翻译
点云是3D内容的至关重要表示,在虚拟现实,混合现实,自动驾驶等许多领域已广泛使用,随着数据中点数的增加,如何有效地压缩点云变为一个具有挑战性的问题。在本文中,我们提出了一组基于贴片的点云压缩的重大改进,即用于熵编码的可学习上下文模型,用于采样质心点的OCTREE编码以及集成的压缩和训练过程。此外,我们提出了一个对抗网络,以改善重建过程中点的均匀性。我们的实验表明,改进的基于斑块的自动编码器在稀疏和大规模点云上的速率延伸性能方面优于最先进的。更重要的是,我们的方法可以在确保重建质量的同时保持短时间的压缩时间。
translated by 谷歌翻译
Point cloud completion is a generation and estimation issue derived from the partial point clouds, which plays a vital role in the applications in 3D computer vision. The progress of deep learning (DL) has impressively improved the capability and robustness of point cloud completion. However, the quality of completed point clouds is still needed to be further enhanced to meet the practical utilization. Therefore, this work aims to conduct a comprehensive survey on various methods, including point-based, convolution-based, graph-based, and generative model-based approaches, etc. And this survey summarizes the comparisons among these methods to provoke further research insights. Besides, this review sums up the commonly used datasets and illustrates the applications of point cloud completion. Eventually, we also discussed possible research trends in this promptly expanding field.
translated by 谷歌翻译
本文提出了解码器 - 侧交叉分辨率合成(CRS)模块,以追求更好的压缩效率超出最新的通用视频编码(VVC),在那里我们在原始高分辨率(HR)处编码帧内帧,以较低的分辨率压缩帧帧间( LR),然后通过在先前的HR帧内和相邻的LR帧间帧内解解码LR帧间帧间帧帧。对于LR帧间帧,设计运动对准和聚合网络(MAN)以产生时间汇总的运动表示,以最佳保证时间平滑度;使用另一个纹理补偿网络(TCN)来生成从解码的HR帧内帧的纹理表示,以便更好地增强空间细节;最后,相似性驱动的融合引擎将运动和纹理表示合成为Upscale LR帧帧,以便去除压缩和分辨率重新采样噪声。我们使用所提出的CRS增强VVC,显示平均为8.76%和11.93%BJ {\ O} NTEGAARD Delta率(BD速率)分别在随机接入(RA)和低延延迟P(LDP)设置中的最新VVC锚点。此外,对基于最先进的超分辨率(SR)的VVC增强方法和消融研究的实验比较,进一步报告了所提出的算法的卓越效率和泛化。所有材料都将在HTTPS://njuvision.github.io /crs上公开进行可重复的研究。
translated by 谷歌翻译
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。
translated by 谷歌翻译
我们认为,作为离散位置向量值体积功能的采样点云的属性。为了压缩所提供的位置属性,我们压缩体积函数的参数。我们通过平铺空间成块,并通过基于坐标的,或隐式的,神经网络的偏移较每个块中的函数的体积函数建模。输入到网络包括空间坐标和每个块的潜矢量。我们代表使用区域自适应分级的系数潜矢量变换在MPEG基于几何形状的点云的编解码器G-PCC使用(RAHT)。的系数,这是高度可压缩的,是速率 - 失真通过在自动解码器配置的速率 - 失真拉格朗日损失由反向传播最优化。结果由2-4分贝优于RAHT。这是第一工作由局部坐标为基础的神经网络为代表的压缩体积的功能。因此,我们希望它是适用超越的点云,例如高分辨率的神经辐射场的压缩。
translated by 谷歌翻译
开发了一种基于变换器的图像压缩(TIC)方法,其重用了具有配对主和超编码器解码器的规范变形AutoEncoder(VAE)架构。主要和超编码器包括一系列神经转换单元(NTU),以分析和聚合重要信息以进行更紧凑的输入图像表示,而解码器镜像编码器侧操作以生成从压缩的像素域图像重建。比特流。每个NTU由Swin变压器块(STB)和卷积层(CONV)组成,以最佳地嵌入远程和短程信息;同时,设计了一种休闲的注意模块(CAM),用于潜在特征的自适应上下文建模,以利用超自行性前提。具有最先进的方法的TIC竞争对手,包括基于深度卷积神经网络(CNNS)的学习图像编码(LIC)方法以及最近批准的多功能视频编码(VVC)标准的基于规则的基于规则的简介,并且需要很多较少的模型参数,例如,降低前导性能LIC减少45%。
translated by 谷歌翻译
我们介绍了NeuralVDB,它通过利用机器学习的最新进步来提高现有的行业标准,以有效地存储稀疏体积数据,表示VDB。我们的新型混合数据结构可以通过数量级来减少VDB体积的内存足迹,同时保持其灵活性,并且只会产生一个小(用户控制的)压缩误差。具体而言,NeuralVDB用多个层次神经网络替换了浅和宽VDB树结构的下节点,这些神经网络分别通过神经分类器和回归器分别编码拓扑和价值信息。这种方法已证明可以最大化压缩比,同时保持高级VDB数据结构提供的空间适应性。对于稀疏的签名距离字段和密度量,我们已经观察到从已经压缩的VDB输入中的$ 10 \ times $ $ $ \ $ 100 \ $ 100 \ $ 100 \ $ 100 \ $ 100的压缩比,几乎没有可视化伪像。我们还展示了其在动画稀疏体积上的应用如何加速训练并产生时间连贯的神经网络。
translated by 谷歌翻译
Point clouds are characterized by irregularity and unstructuredness, which pose challenges in efficient data exploitation and discriminative feature extraction. In this paper, we present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology as a completely regular 2D point geometry image (PGI) structure, in which coordinates of spatial points are captured in colors of image pixels. \mr{Intuitively, Flattening-Net implicitly approximates a locally smooth 3D-to-2D surface flattening process while effectively preserving neighborhood consistency.} \mr{As a generic representation modality, PGI inherently encodes the intrinsic property of the underlying manifold structure and facilitates surface-style point feature aggregation.} To demonstrate its potential, we construct a unified learning framework directly operating on PGIs to achieve \mr{diverse types of high-level and low-level} downstream applications driven by specific task networks, including classification, segmentation, reconstruction, and upsampling. Extensive experiments demonstrate that our methods perform favorably against the current state-of-the-art competitors. We will make the code and data publicly available at https://github.com/keeganhk/Flattening-Net.
translated by 谷歌翻译
Accurate detection of objects in 3D point clouds is a central problem in many applications, such as autonomous navigation, housekeeping robots, and augmented/virtual reality. To interface a highly sparse LiDAR point cloud with a region proposal network (RPN), most existing efforts have focused on hand-crafted feature representations, for example, a bird's eye view projection. In this work, we remove the need of manual feature engineering for 3D point clouds and propose VoxelNet, a generic 3D detection network that unifies feature extraction and bounding box prediction into a single stage, end-to-end trainable deep network. Specifically, VoxelNet divides a point cloud into equally spaced 3D voxels and transforms a group of points within each voxel into a unified feature representation through the newly introduced voxel feature encoding (VFE) layer. In this way, the point cloud is encoded as a descriptive volumetric representation, which is then connected to a RPN to generate detections. Experiments on the KITTI car detection benchmark show that VoxelNet outperforms the state-of-the-art LiDAR based 3D detection methods by a large margin. Furthermore, our network learns an effective discriminative representation of objects with various geometries, leading to encouraging results in 3D detection of pedestrians and cyclists, based on only LiDAR.
translated by 谷歌翻译
Intelligent mesh generation (IMG) refers to a technique to generate mesh by machine learning, which is a relatively new and promising research field. Within its short life span, IMG has greatly expanded the generalizability and practicality of mesh generation techniques and brought many breakthroughs and potential possibilities for mesh generation. However, there is a lack of surveys focusing on IMG methods covering recent works. In this paper, we are committed to a systematic and comprehensive survey describing the contemporary IMG landscape. Focusing on 110 preliminary IMG methods, we conducted an in-depth analysis and evaluation from multiple perspectives, including the core technique and application scope of the algorithm, agent learning goals, data types, targeting challenges, advantages and limitations. With the aim of literature collection and classification based on content extraction, we propose three different taxonomies from three views of key technique, output mesh unit element, and applicable input data types. Finally, we highlight some promising future research directions and challenges in IMG. To maximize the convenience of readers, a project page of IMG is provided at \url{https://github.com/xzb030/IMG_Survey}.
translated by 谷歌翻译
本文档描述了基于深度学习的点云几何编解码器和基于深度学习的点云关节几何和颜色编解码器,并提交给2022年1月发出的JPEG PLENO点云编码的建议。拟议的编解码器是基于最新的。基于深度学习的PC几何编码的发展,并提供了呼吁提案的一些关键功能。拟议的几何编解码器提供了一种压缩效率,可超过MPEG G-PCC标准和胜过MPEG的效率,或者与V-PCC Intra Intra Interra Interra Intra标准的竞争力均超过了jpeg呼叫提案测试集;但是,由于需要克服的质量饱和效应,关节几何和颜色编解码器不会发生同样的情况。
translated by 谷歌翻译
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.
translated by 谷歌翻译