Object point cloud classification has drawn great research attention since the release of benchmarking datasets, such as the ModelNet and the ShapeNet. These benchmarks assume point clouds covering complete surfaces of object instances, for which plenty of high-performing methods have been developed. However, their settings deviate from those often met in practice, where, due to (self-)occlusion, a point cloud covering partial surface of an object is captured from an arbitrary view. We show in this paper that performance of existing point cloud classifiers drops drastically under the considered single-view, partial setting; the phenomenon is consistent with the observation that semantic category of a partial object surface is less ambiguous only when its distribution on the whole surface is clearly specified. To this end, we argue for a single-view, partial setting where supervised learning of object pose estimation should be accompanied with classification. Technically, we propose a baseline method of Pose-Accompanied Point cloud classification Network (PAPNet); built upon SE(3)-equivariant convolutions, the PAPNet learns intermediate pose transformations for equivariant features defined on vector fields, which makes the subsequent classification easier (ideally) in the category-level, canonical pose. By adapting existing ModelNet40 and ScanNet datasets to the single-view, partial setting, experiment results can verify the necessity of object pose estimation and superiority of our PAPNet to existing classifiers.
In this paper, based on the assumption that the object boundaries (e.g., buildings) from the over-view data should coincide with footprints of façade 3D points generated from street-view photogrammetric images, we aim to address this problem by proposing a fully automated geo-registration method for cross-view data, which utilizes semantically segmented object boundaries as view-invariant features under a global optimization framework through graph-matching: taking the over-view point clouds generated from stereo/multi-stereo satellite images and the street-view point clouds generated from mon…
Tsinghua University（清华大学）；Huawei Technologies Canada Co Ltd（华为技术加拿大有限公司）；OPPO Research Institute（OPPO研究院）
This paper presents a view-guided solution for the task of point cloud completion. Unlike most existing methods directly inferring the missing points using shape priors, we address this task by introducing ViPC (view-guided point cloud completion) that takes the missing crucial global structure information from an extra single-view image. By leveraging a framework that sequentially performs effective cross-modality and cross-level fusions, our method achieves significantly superior results over typical existing solutions on a new large-scale dataset we collect for the view-guided point cloud c…
Learning A Locally Unified 3D Point Cloud for View Synthesis
City University of Hong Kong（香港城市大学）；City University of Hong Kong Shenzhen Research Institute（香港城市大学深圳研究院）；Caritas Institute of Higher Education（明爱专上学院）
DeepGlint（深瞐科技）；China University of Mining and Technology（中国矿业大学）
Great progress has been made in point cloud classification with learning-based methods. However, complex scene and sensor inaccuracy in real-world application make point cloud data suffer from corruptions, such as occlusion, noise and outliers. In this work, we propose Point-Voxel based Adaptive (PV-Ada) feature abstraction for robust point cloud classification under various corruptions. Specifically, the proposed framework iteratively voxelize the point cloud and extract point-voxel feature with shared local encoding and Transformer. Then, adaptive max-pooling is proposed to robustly aggregat…
University of Amsterdam（阿姆斯特丹大学）；Google Research（谷歌研究院）
In this paper the argument is made that for true novel view synthesis of objects, where the object can be synthesized from any viewpoint, an explicit 3D shape representation isdesired. Our method estimates point clouds to capture the geometry of the object, which can be freely rotated into the desired view and then projected into a new image. This image, however, is sparse by nature and hence this coarse view is used as the input of an image completion network to obtain the dense target view. The point cloud is obtained using the predicted pixel-wise depth map, estimated from a single RGB inpu…
Although 3D point cloud classification neural network models have been widely used, the in-depth interpretation of the activation of the neurons and layers is still a challenge. We propose a novel approach, named Relevance Flow, to interpret the hidden semantics of 3D point cloud classification neural networks. It delivers the class Relevance to the activated neurons in the intermediate layers in a back-propagation manner, and associates the activation of neurons with the input points to visualize the hidden semantics of each layer. Specially, we reveal that the 3D point cloud classification n…
3D perception, especially point cloud classification, has achieved substantial progress. However, in real-world deployment, point cloud corruptions are inevitable due to the scene complexity, sensor inaccuracy, and processing imprecision. In this work, we aim to rigorously benchmark and analyze point cloud classification under corruptions. To conduct a systematic investigation, we first provide a taxonomy of common 3D corruptions and identify the atomic corruptions. Then, we perform a comprehensive evaluation on a wide range of representative point cloud models to understand their robustness a…
Shanghai Jiao Tong University（上海交通大学）；Foshan Woman and Children’s Hospital（佛山市妇幼保健院）
Understanding the implication of point cloud is still challenging to achieve the goal of classification or segmentation due to the irregular and sparse structure of point cloud. As we have known, PointNet architecture as a ground-breaking work for point cloud which can learn efficiently shape features directly on unordered 3D point cloud and have achieved favorable performance. However, this model fail to consider the fine-grained semantic information of local structure for point cloud. Afterwards, many valuable works are proposed to enhance the performance of PointNet by means of semantic fea…
Mines ParisTech（巴黎高等矿业学院）；PSL Research University（巴黎文理研究大学）；Centre for Robotics（机器人中心）
In this article we describe a new convolutional neural network (CNN) to classify 3D point clouds of urban or indoor scenes. Solutions are given to the problems encountered working on scene point clouds, and a network is described that allows for point classification using only the position of points in a multi-scale neighborhood. On the reduced-8 Semantic3D benchmark [Hackel et al., 2017], this network, ranked second, beats the state of the art of point classification methods (those not using a regularization step).
Australian National University（澳大利亚国立大学）；Data61-CSIRO（Data61-联邦科学与工业研究组织）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）
Zero-shot learning, the task of learning to recognize new classes not seen during training, has received considerable attention in the case of 2D image classification. However despite the increasing ubiquity of 3D sensors, the corresponding 3D point cloud classification problem has not been meaningfully explored and introduces new challenges. This paper extends, for the first time, transductive Zero-Shot Learning (ZSL) and Generalized Zero-Shot Learning (GZSL) approaches to the domain of 3D point cloud classification. To this end, a novel triplet loss is developed that takes advantage of unlab…
Multi-view point cloud registration is a hot topic in the communities of multimedia technology and artificial intelligence (AI). In this paper, we propose a framework to reconstruct the 3D models by the multi-view point cloud registration algorithm with adaptive convergence threshold, and subsequently apply it to 3D model retrieval. The iterative closest point (ICP) algorithm is implemented combining with the motion average algorithm for the registration of multi-view point clouds. After the registration process, we design applications for 3D model retrieval. The geometric saliency map is comp…
School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院）
In this paper, we propose a point cloud classification method based on graph neural network and manifold learning. Different from the conventional point cloud analysis methods, this paper uses manifold learning algorithms to embed point cloud features for better considering the geometric continuity on the surface. Then, the nature of point cloud can be acquired in low dimensional space, and after being concatenated with features in the original three-dimensional (3D)space, both the capability of feature representation and the classification network performance can be improved. We pro-pose two …
College of Science, Beijing Forestry University（北京林业大学理学院）
Terrestrial laser scanning technology provides an efficient and accuracy solution for acquiring three-dimensional information of plants. The leaf-wood classification of plant point cloud data is a fundamental step for some forestry and biological research. An automatic sampling and training method for classification was proposed based on tree point cloud data. The plane fitting method was used for selecting leaf sample points and wood sample points automatically, then two local features were calculated for training and classification by using support vector machine (SVM) algorithm. The point c…
HKUST（香港科技大学）；Alibaba A.I. Labs（阿里巴巴人工智能实验室）；City University of Hong Kong（香港城市大学）；Simon Fraser University（西蒙弗雷泽大学）
In this work, we propose an end-to-end framework to learn local multi-view descriptors for 3D point clouds. To adopt a similar multi-view representation, existing studies use hand-crafted viewpoints for rendering in a preprocessing stage, which is detached from the subsequent descriptor learning stage. In our framework, we integrate the multi-view rendering into neural networks by using a differentiable renderer, which allows the viewpoints to be optimizable parameters for capturing more informative local context of interest points. To obtain discriminative descriptors, we also design a soft-v…
Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlook
Xinjiang University（新疆大学）；Institute of Semiconductors, Chinese Academy of Sciences（中国科学院半导体研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Beihang University（北京航空航天大学）
Many point cloud classification methods are developed under the assumption that all point clouds in the dataset are well aligned with the canonical axes so that the 3D Cartesian point coordinates can be employed to learn features. When input point clouds are not aligned, the classification performance drops significantly. In this work, we focus on a mathematically transparent point cloud classification method called PointHop, analyze its reason for failure due to pose variations, and solve the problem by replacing its pose dependent modules with rotation invariant counterparts. The proposed me…
University of Technology Sydney（悉尼科技大学）；Nokia Technologies（诺基亚科技）；Tsinghua University（清华大学）
With the development of numerous 3D sensing technologies, object registration on cross-source point cloud has aroused researchers' interests. When the point clouds are captured from different kinds of sensors, there are large and different kinds of variations. In this study, we address an even more challenging case in which the differently-source point clouds are acquired from a real street view. One is produced directly by the LiDAR system and the other is generated by using VSFM software on image sequence captured from RGB cameras. When it confronts to large scale point clouds, previous meth…
Mines ParisTech（巴黎高等矿业学院）；PSL Research University（巴黎文理研究大学）
This paper introduces a new definition of multiscale neighborhoods in 3D point clouds. This definition, based on spherical neighborhoods and proportional subsampling, allows the computation of features with a consistent geometrical meaning, which is not the case when using k-nearest neighbors. With an appropriate learning strategy, the proposed features can be used in a random forest to classify 3D points. In this semantic classification task, we show that our multiscale features outperform state-of-the-art features using the same experimental conditions. Furthermore, their classification powe…
We present a powerful method to extract per-point semantic class labels from aerialphotogrammetry data. Labeling this kind of data is important for tasks such as environmental modelling, object classification and scene understanding. Unlike previous point cloud classification methods that rely exclusively on geometric features, we show that incorporating color information yields a significant increase in accuracy in detecting semantic classes. We test our classification method on three real-world photogrammetry datasets that were generated with Pix4Dmapper Pro, and with varying point densities…
Standard spatial convolutions assume input data with a regular neighborhood structure. Existing methods typically generalize convolution to the irregular point cloud domain by fixing a regular "view" through e.g. a fixed neighborhood size, where the convolution kernel size remains the same for each point. However, since point clouds are not as structured as images, the fixed neighbor number gives an unfortunate inductive bias. We present a novel graph convolution named Difference Graph Convolution (diffConv), which does not rely on a regular view. diffConv operates on spatially-varying and den…
3D object recognition has attracted wide research attention in the field of multimedia and computer vision. With the recent proliferation of deep learning, various deep models with different representations have achieved the state-of-the-art performance. Among them, point cloud and multi-view based 3D shape representations are promising recently, and their corresponding deep models have shown significant performance on 3D shape recognition. However, there is little effort concentrating point cloud data and multi-view data for 3D shape representation, which is, in our consideration, beneficial …
Jeonbuk National University（全北国立大学）；Kyungpook National University（庆北国立大学）
A laser scanner can easily acquire the geometric data of physical environments in the form of a point cloud. Recognizing objects from a point cloud is often required for industrial 3D reconstruction, which should include not only geometry information but also semantic information. However, recognition process is often a bottleneck in 3D reconstruction because it requires expertise on domain knowledge and intensive labor. To address this problem, various methods have been developed to recognize objects by retrieving the corresponding model in the database from an input geometry query. In recent…
This paper introduces a novel network architecture for the classification of large-scale point clouds. The network is used to classify metadata from cuneiform tablets. As more than half a million tablets remain unprocessed, this can help create an overview of the tablets. The network is tested on a comparison dataset and obtains state-of-the-art performance. We also introduce new metadata classification tasks on which the network shows promising results. Finally, we introduce the novel Maximum Attention visualization, demonstrating that the trained network focuses on the intended features. Cod…
The Worse The Better: Content-Aware Viewpoint Generation Network for Projection-related Point Cloud Quality Assessment
School of Automation, Nanjing University of Science and Technology（南京理工大学自动化学院）；School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）
The point cloud is gaining prominence as a method for representing 3D shapes, but its irregular format poses a challenge for deep learning methods. The common solution of transforming the data into a 3D voxel grid introduces its own challenges, mainly large memory size. In this paper we propose a novel 3D point cloud representation called 3D Modified Fisher Vectors (3DmFV). Our representation is hybrid as it combines the discrete structure of a grid with continuous generalization of Fisher vectors, in a compact and computationally efficient way. Using the grid enables us to design a new CNN ar…
Australian National University（澳大利亚国立大学）；Data61-CSIRO（联邦科学与工业研究组织Data61）
Point cloud analysis is attracting attention from Artificial Intelligence research since it can be widely used in applications such as robotics, Augmented Reality, self-driving. However, it is always challenging due to irregularities, unorderedness, and sparsity. In this article, we propose a novel network named Dense-Resolution Network (DRNet) for point cloud analysis. Our DRNet is designed to learn local point features from the point cloud in different resolutions. In order to learn local point groups more effectively, we present a novel grouping method for local neighborhood searching and a…
Indian Institute of Technology Gandhinagar（印度理工学院甘地纳加尔分校）
Point cloud segmentation and classification are some of the primary tasks in 3D computer vision with applications ranging from augmented reality to robotics. However, processing point clouds using deep learning-based algorithms is quite challenging due to the irregular point formats. Voxelization or 3D grid-based representation are different ways of applying deep neural networks to this problem. In this paper, we propose PointResNet, a residual block-based approach. Our model directly processes the 3D points, using a deep neural network for the segmentation and classification tasks. The main c…
Media Communications Lab（媒体通信实验室）；University of Southern California（南加州大学）；Tencent Media Lab（腾讯媒体实验室）；Tencent America（腾讯美国）
In contrast to supervised backpropagation-based feature learning in deep neural networks (DNNs), an unsupervised feedforward feature (UFF) learning scheme for joint classification and segmentation of 3D point clouds is proposed in this work. The UFF method exploits statistical correlations of points in a point cloud set to learn shape and point features in a one-pass feedforward manner through a cascaded encoder-decoder architecture. It learns global shape features through the encoder and local point features through the concatenated encoder-decoder architecture. The extracted features of an i…
University of Waterloo（滑铁卢大学）；University of Oxford（牛津大学）
Although accurate and fast point cloud classification is a fundamental task in 3D applications, it is difficult to achieve this purpose due to the irregularity and disorder of point clouds that make it challenging to achieve effective and efficient global discriminative feature learning. Lately, 3D Transformers have been adopted to improve point cloud processing. Nevertheless, massive Transformer layers tend to incur huge computational and memory costs. This paper presents a novel hierarchical framework that incorporates convolution with Transformer for point cloud classification, named 3D Con…
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Tandon School of Engineering, New York University（纽约大学坦登工程学院）
Airborne light detection and ranging (LiDAR) plays an increasingly significant role in urban planning, topographic mapping, environmental monitoring, power line detection and other fields thanks to its capability to quickly acquire large-scale and high-precision ground information. To achieve point cloud classification, previous studies proposed point cloud deep learning models that can directly process raw point clouds based on PointNet-like architectures. And some recent works proposed graph convolution neural network based on the inherent topology of point clouds. However, the above point c…
King Abdullah University of Science Technology (KAUST)（阿卜杜拉国王科技大学）
Multi-view projection methods have demonstrated promising performance on 3D understanding tasks like 3D classification and segmentation. However, it remains unclear how to combine such multi-view methods with the widely available 3D point clouds. Previous methods use unlearned heuristics to combine features at the point level. To this end, we introduce the concept of the multi-view point cloud (Voint cloud), representing each 3D point as a set of features extracted from several view-points. This novel 3D Voint cloud representation combines the compactness of 3D point cloud representation with …
Hong Kong University of Science and Technology（香港科技大学）；Shenzhen Zhuke Innovation Technology（深圳珠科创新技术）
Critical to the registration of point clouds is the establishment of a set of accurate correspondences between points in 3D space. The correspondence problem is generally addressed by the design of discriminative 3D local descriptors on the one hand, and the development of robust matching strategies on the other hand. In this work, we first propose a multi-view local descriptor, which is learned from the images of multiple views, for the description of 3D keypoints. Then, we develop a robust matching approach, aiming at rejecting outlier matches based on the efficient inference via belief prop…
Beijing Forestry University（北京林业大学）；Research Institute of Petroleum Exploration and Development, Petrochina（中国石油勘探开发研究院）
Terrestrial laser scanning (TLS) can obtain tree point cloud with high precision and high density. Efficient classification of wood points and leaf points is essential to study tree structural parameters and ecological characteristics. By using both the intensity and spatial information, a three-step classification and verification method was proposed to achieve automated wood-leaf classification. Tree point cloud was classified into wood points and leaf points by using intensity threshold, neighborhood density and voxelization successively. Experiment was carried in Haidian Park, Beijing, and…
Tsinghua University（清华大学）；Xiamen University（厦门大学）；University of Maryland, College Park（马里兰大学帕克分校）
Three-dimensional (3D) shape recognition has drawn much research attention in the field of computer vision. The advances of deep learning encourage various deep models for 3D feature representation. For point cloud and multi-view data, two popular 3D data modalities, different models are proposed with remarkable performance. However the relation between point cloud and views has been rarely investigated. In this paper, we introduce Point-View Relation Network (PVRNet), an effective network designed to well fuse the view features and the point cloud feature with a proposed relation score module…
Worcester Polytechnic Institute（伍斯特理工学院）；Volvo Car Technology USA（沃尔沃汽车技术美国公司）
Point cloud patterns are hard to learn because of the implicit local geometry features among the orderless points. In recent years, point cloud representation in 2D space has attracted increasing research interest since it exposes the local geometry features in a 2D space. By projecting those points to a 2D feature map, the relationship between points is inherited in the context between pixels, which are further extracted by a 2D convolutional neural network. However, existing 2D representing methods are either accuracy limited or time-consuming. In this paper, we propose a novel 2D representa…
S-Lab, Nanyang Technological University（南洋理工大学 S-Lab）；SenseTime-CUHK Joint Lab, The Chinese University of Hong Kong（香港中文大学商汤科技联合实验室）；Sensetime Research（商汤科技研究院）；Shanghai AI Laboratory（上海人工智能实验室）；Department of Automation, Tsinghua University（清华大学自动化系）；University of Chinese Academy of Sciences（中国科学院大学）；Digital Medical Research Center, School of Basic Medical Science, Fudan University（复旦大学基础医学院数字医学研究中心）；School of Software, BNRist, Tsinghua University（清华大学软件学院）；Wayne State University（韦恩州立大学）；State key Laboratory for novel software technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；DeepGlint（格灵深瞳）；Shanghai Jiao Tong University（上海交通大学）；Sichuan University（四川大学）
As real-scanned point clouds are mostly partial due to occlusions and viewpoints, reconstructing complete 3D shapes based on incomplete observations becomes a fundamental problem for computer vision. With a single incomplete point cloud, it becomes the partial point cloud completion problem. Given multiple different observations, 3D reconstruction can be addressed by performing partial-to-partial point cloud registration. Recently, a large-scale Multi-View Partial (MVP) point cloud dataset has been released, which consists of over 100,000 high-quality virtual-scanned partial point clouds. Base…
College of Science, Beijing Forestry University（北京林业大学理学院）
The accurate classification of plant organs is a key step in monitoring the growing status and physiology of plants. A classification method was proposed to classify the leaves and stems of potted plants automatically based on the point cloud data of the plants, which is a nondestructive acquisition. The leaf point training samples were automatically extracted by using the three-dimensional convex hull algorithm, while stem point training samples were extracted by using the point density of a two-dimensional projection. The two training sets were used to classify all the points into leaf point…
In this paper, we address the problem of reconstructing an object's surface from a single image using generative networks. First, we represent a 3D surface with an aggregation of dense point clouds from multiple views. Each point cloud is embedded in a regular 2D grid aligned on an image plane of a viewpoint, making the point cloud convolution-favored and ordered so as to fit into deep network architectures. The point clouds can be easily triangulated by exploiting connectivities of the 2D grids to form mesh-based surfaces. Second, we propose an encoder-decoder network that generates such kind…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Many recent works show that a spatial manipulation module could boost the performances of deep neural networks (DNNs) for 3D point cloud analysis. In this paper, we aim to provide an insight into spatial manipulation modules. Firstly, we find that the smaller the rotational degree of freedom (RDF) of objects is, the more easily these objects are handled by these DNNs. Then, we investigate the effect of the popular T-Net module and find that it could not reduce the RDF of objects. Motivated by the above two issues, we propose a rotation transformation network for point cloud analysis, called RT…
United States Air Force Institute of Technology（美国空军理工学院）
This paper describes a neural network layer, named Ursa, that uses a constellation of points to learn classification information from point cloud data. Unlike other machine learning classification problems where the task is to classify an individual high-dimensional observation, in a point-cloud classification problem the goal is to classify a set of d-dimensional observations. Because a point cloud is a set, there is no ordering to the collection of points in a point-cloud classification problem. Thus, the challenge of classifying point clouds inputs is in building a classifier which is agnos…
Leveraging Single-View Images for Unsupervised 3D Point Cloud Completion
City University of Hong Kong（香港城市大学）；Bio-Computing Research Center, Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）生物计算研究中心）；Shenzhen Key Laboratory of Visual Object Detection and Recognition（深圳市视觉目标检测与识别重点实验室）
While several convolution-like operators have recently been proposed for extracting features out of point clouds, down-sampling an unordered point cloud in a deep neural network has not been rigorously studied. Existing methods down-sample the points regardless of their importance for the output. As a result, some important points in the point cloud may be removed, while less valuable points may be passed to the next layers. In contrast, adaptive down-sampling methods sample the points by taking into account the importance of each point, which varies based on the application, task and training…
As 3D point cloud analysis has received increasing attention, the insufficient scale of point cloud datasets and the weak generalization ability of networks become prominent. In this paper, we propose a simple and effective augmentation method for the point cloud data, named PointCutMix, to alleviate those problems. It finds the optimal assignment between two point clouds and generates new training data by replacing the points in one sample with their optimal assigned pairs. Two replacement strategies are proposed to adapt to the accuracy or robustness requirement for different tasks, one of w…
We present PointAugment, a new auto-augmentation framework that automatically optimizes and augments point cloud samples to enrich the data diversity when we train a classification network. Different from existing auto-augmentation methods for 2D images, PointAugment is sample-aware and takes an adversarial learning strategy to jointly optimize an augmentor network and a classifier network, such that the augmentor can learn to produce augmented samples that best fit the classifier. Moreover, we formulate a learnable point augmentation function with a shape-wise transformation and a point-wise …
ModelNet40-E: An Uncertainty-Aware Benchmark for Point Cloud Classification
School of Computing and Artificial Intelligence, Southwest Jiaotong University（计算机与人工智能学院，西南交通大学）；Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Chengdu, China（可持续城市智能交通工程研究中心，教育部，成都，中国）
本文提出带逐点不确定性标注的 ModelNet40-E 噪声点云基准，并评估 PointNet、DGCNN 和 Point Transformer v3，表明 Point Transformer v3 校准更优。
Test-Time Augmentation for 3D Point Cloud Classification and Segmentation
The Hong Kong University of Science and Technology（香港科技大学）；VinAI Research（VinAI研究院）；Singapore Management University（新加坡管理大学）；Trinity College Dublin（都柏林圣三一学院）
