Lossy Point Cloud Geometry Compression via Region-Wise Processing

Abstract. Training LiDAR point clouds object detectors requires a significant amount of annotated data, which is time-consuming and effort-demanding. Although weakly supervised 3D LiDAR-based methods have been proposed to reduce the annotation cost, their performance could be further improved. In this work, we propose a weakly supervised LiDAR-based point clouds vehicle detector that does not require any labels for the proposal generation stage and needs only a few labels for the refinement stage. It comprises two primary modules. The first is an unsupervised proposal generation module based on the geometry of point clouds. The second is the pseudo-label refinement module. We validate our method on two point clouds based object detection datasets, namely KITTI and ONCE, and compare it with various existing weakly supervised point clouds object detection methods. The experimental results demonstrate the method’s effectiveness with a small amount of labeled LiDAR point clouds.

Point clouds have been gaining importance as a solution to the problem of efficient representation of 3D geometric and visual information. They are commonly represented by large amounts of data, and compression schemes are important for their manipulation transmission and storing. However, the selection of appropriate compression schemes requires effective quality evaluation. In this work a subjective quality evaluation of point clouds using a surface representation is analyzed. Using a set of point cloud data objects encoded with the popular octree pruning method with different qualities, a subjective evaluation was designed. The point cloud geometry was presented to observers in the form of a movie showing the 3D Poisson reconstructed surface without textural information with the point of view changing in time. Subjective evaluations were performed in three different laboratories. Scores obtained from each test were correlated and no statistical differences were observed. Scores were also correlated with previous subjective tests and a good correlation was obtained when compared with mesh rendering in 2D monitors. Moreover, the results were correlated with state of the art point cloud objective metrics revealing poor correlation. Likewise, the correlation with a subjective test using a different representation of the point cloud data also showed poor correlation. These results suggest the need for more reliable objective quality metrics and further studies on adequate point cloud data representations.

The geometry of a point cloud is commonly represented by an octree recursively decomposing a 3D volume into eight child sub-volumes. Said volumes and sub-volumes are associated with nodes and child-nodes of the octree. The geometry is defined by the occupancy information indicating the presence or not of a point in each of the sub-volumes. This naturally leads to an eight-bit occupancy information to be coded for each internal node of the tree. This paper introduces a new binarization scheme to efficiently compress the occupancy information using an optimal set of binary entropy coders. Then, it is shown how using the occupancy information of neighbouring nodes helps to compress the occupancy bits associated with the child nodes of the current node. This information is used to contextualise the binarization scheme by computing, firstly a neighbour configuration, secondly a number of neighbours with occupied child nodes adjacent to the current child node, and thirdly an intra predictor. Objective results show lossless geometry compression gains between 60% and 75% on virtual reality oriented dense point clouds used by MPEG, reaching sub-bit per point bit-rates for the lossless intra coding of such point clouds. Solid gains (between 5% and 25% depending upon the sampling) are also observed on sparse point clouds captured by a LiDAR (Light Detection and Ranging) device attached to a moving vehicle or representing 3D maps.

This paper presents a novel end-to-end Learned Point Cloud Geometry\nCompression (a.k.a., Learned-PCGC) framework, to efficiently compress the point\ncloud geometry (PCG) using deep neural networks (DNN) based variational\nautoencoders (VAE). In our approach, PCG is first voxelized, scaled and\npartitioned into non-overlapped 3D cubes, which is then fed into stacked 3D\nconvolutions for compact latent feature and hyperprior generation. Hyperpriors\nare used to improve the conditional probability modeling of latent features. A\nweighted binary cross-entropy (WBCE) loss is applied in training while an\nadaptive thresholding is used in inference to remove unnecessary voxels and\nreduce the distortion. Objectively, our method exceeds the geometry-based point\ncloud compression (G-PCC) algorithm standardized by well-known Moving Picture\nExperts Group (MPEG) with a significant performance margin, e.g., at least 60%\nBD-Rate (Bjontegaard Delta Rate) gains, using common test datasets.\nSubjectively, our method has presented better visual quality with smoother\nsurface reconstruction and appealing details, in comparison to all existing\nMPEG standard compliant PCC methods. Our method requires about 2.5MB parameters\nin total, which is a fairly small size for practical implementation, even on\nembedded platform. Additional ablation studies analyze a variety of aspects\n(e.g., cube size, kernels, etc) to explore the application potentials of our\nlearned-PCGC.\n

Point cloud data have been put under the spotlight by many applications that play an increasingly important role in our every day lives. Their large size and ever-growing prevalent use cases have raised the interest in specialized compression algorithms for point cloud data. In this paper we propose a lossless intra-frame encoder for point cloud geometry. It relies on a single projection of the entire point cloud on a predetermined plane, combined with a context-adaptive binary arithmetic encoder. Our approach simplifies the current best performing approach for intra-frame compression. The experimental results indicate that our proposal not only improves the performance of all other intra-frame approaches, but it even surpasses the performance of state-of-the-art inter-frame approaches. Furthermore, we suggest to replace the adaptive encoder with a semi-adaptive approach for further performance gains.

The increase in popularity of point-cloud-oriented applications has triggered the development of specialized compression algorithms. In this paper, a novel algorithm is developed for the lossless geometry compression of voxelized point clouds following an intra-frame design. The encoded voxels are arranged into runs and are encoded through a single-pass application directly on the voxel domain. This is done without representing the point cloud via an octree nor rendering the voxel space through an occupancy matrix, therefore decreasing the memory requirements of the method. Each run is compressed using a context-adaptive arithmetic encoder yielding state-of-the-art compression results, with gains of up to 15% over TMC13, MPEG's standard for point cloud geometry compression. Several proposed contributions accelerate the calculations of each run's probability limits prior to arithmetic encoding. As a result, the encoder attains a low computational complexity described by a linear relation to the number of occupied voxels leading to an average speedup of 1.8 over TMC13 in encoding speeds. Various experiments are conducted assessing the proposed algorithm's state-of-the-art performance in terms of compression ratio and encoding speeds.

3D and free-viewpoint video has been moving towards solid-scene representation using meshes and point clouds. Point-cloud processing requires much less computation and the points in the cloud are minimally represented by their geometry (3D position) and color. A common point-cloud geometry compression method is the octree representation, which acts on individual frames. We present a lossless inter-frame compression method for pointcloud geometry, by reordering each octree based on previous frames prior to entropy coding. Results show that compared to the octree representation, the proposed solution offers an average rate reduction of 30%, while entropy-coding of the octree yields an average rate reduction of 24%.

In this paper, we investigate two fundamental problems of inter-prediction for Light Detection and Ranging (LiDAR) point cloud geometries: motion estimation (ME) and coding structure under the inter-exploration model of geometry-based point cloud compression (G-PCC). Under the inter-exploration model of G-PCC, the key to a good ME algorithm is to design an accurate criterion for estimating the bit cost of an octree node. In the previous work, a logarithmic relationship between the prediction distortion and the bit cost was used as the criterion. We first note that the multiscale binary prediction residue, instead of the prediction distortion, is the key factor in determining the bit cost. Then, a linear relationship between the number of 1s and 0s in the multiscale binary prediction residue and the bit cost is built and used as the ME criterion. In terms of the coding structure, only the IPPP coding structure is investigated in all previous geometry inter-prediction algorithms. The use of the hierarchical coding structure is first investigated in this paper. We further propose determining the use of the IPPP or hierarchical coding structure at the group of pictures (GoP)-level based on rate distortion optimization to improve the performance. The proposed algorithms are implemented in the inter-exploration model of G-PCC. The experimental results show that compared with the inter-exploration model of G-PCC, the proposed algorithms can provide an average of 2.1% bitrate savings.

We present a study on the impact of packet loss on dynamic 3D point cloud streaming, encoded with MPEG Video-based Point Cloud Compression (V-PCC) standard. We show the distortion when different channels of V-PCC bitstream are lost, with the loss of occupancy and geometry data impacting the quality most significantly. Our results point to the need for better error concealment techniques. We end the paper by presenting preliminary thoughts and experimental results of two naive error concealment techniques in the point cloud domain, for attributes and geometry data, respectively, and highlight the limitations of each.

This work shows an example of a methodology which could be followed to process a crossing geometry with the objective of obtaining and evaluating planar sections.Primitive geometry is reached by profilometry techniques as point cloud geometry and then preprocessed with simple filtering in order to clean it from noise and outliers.Variable geometry on railway crossings requires methods to be then applied in different zones for checking if any local refinement is necessary.Lastly, sections are postprocessed, obtaining an intelligible contour curve to be afterwards visually inspected or as a profile source for multibody software.

Clustering algorithms divide data into meaningful or useful groups, called clusters, such that the intra-cluster similarity is maximized and the inter-cluster similarity is minimized.These discovered clusters can be used to explain the characteristics of the underlying data distribution and thus serve as the foundation for various data mining and analysis techniques.The applications of clustering include characterization of different customer groups based upon purchasing patterns, categorization of documents on the World Wide Web, grouping of genes and proteins that have similar functionality, grouping of spatial locations prone to earth quakes from seismological data, etc. What is CLUTOCLUTO is a software package for clustering low and high dimensional datasets and for analyzing the characteristics of the various clusters.CLUTO provides three different classes of clustering algorithms that operate either directly in the object's feature space or in the object's similarity space.These algorithms are based on the partitional, agglomerative, and graphpartitioning paradigms.A key feature in most of CLUTO's clustering algorithms is that they treat the clustering problem as an optimization process which seeks to maximize or minimize a particular clustering criterion function defined either globally or locally over the entire clustering solution space.CLUTO provides a total of seven different criterion functions that can be used to drive both partitional and agglomerative clustering algorithms, that are described and analyzed in [6,5].Most of these criterion functions have been shown to produce high quality clustering solutions in high dimensional datasets, especially those arising in document clustering.In addition to these criterion functions, CLUTO provides some of the more traditional local criteria (e.g., single-link, complete-link, and UPGMA) that can be used in the context of agglomerative clustering.Furthermore, CLUTO provides graph-partitioning-based clustering algorithms that are well-suited for finding clusters that form contiguous regions that span different dimensions of the underlying feature space.An important aspect of partitional-based criterion-driven clustering algorithms is the method used to optimize this criterion function.CLUTO uses a randomized incremental optimization algorithm that is greedy in nature, has low computational requirements, and has been shown to produce high-quality clustering solutions [6].CLUTO's graphpartitioning-based clustering algorithms utilize high-quality and efficient multilevel graph partitioning algorithms derived from the METIS and hMETIS graph and hypergraph partitioning algorithms [4,3].CLUTO also provides tools for analyzing the discovered clusters to understand the relations between the objects assigned to each cluster and the relations between the different clusters, and tools for visualizing the discovered clustering solutions.CLUTO can identify the features that best describe and/or discriminate each cluster.These set of features can be used to gain a better understanding of the set of objects assigned to each cluster and to provide concise summaries about the cluster's contents.Moreover, CLUTO provides visualization capabilities that can be used to see the relationships between the clusters, objects, and features.CLUTO's algorithms have been optimized for operating on very large datasets both in terms of the number of objects as well as the number of dimensions.This is especially true for CLUTO's algorithms for partitional clustering.These algorithms can quickly cluster datasets with several tens of thousands objects and several thousands of dimensions.Moreover, since most high-dimensional datasets are very sparse, CLUTO directly takes into account this sparsity and requires memory that is roughly linear on the input size.CLUTO's distribution consists of both stand-alone programs (vcluster and scluster) for clustering and analyzing these clusters, as well as, a library via which an application program can access directly the various clustering and analysis algorithms implemented in CLUTO. Outline of CLUTO's ManualCLUTO's manual is organized as follows.Section 2 describe the major changes from the previous release.Section 3 describes the stand-alone programs provided by CLUTO, and discusses its various options and analysis capabilities.Section 4 describes the type of clusters that CLUTO's algorithms can find, and discusses their scalability.Section 5 de-

With the rapid development of smart cities, intelligent navigation, and autonomous driving, how to quickly obtain 3D spatial information of urban buildings and build a high-precision 3D fine model has become a key problem to be solved. As the two-dimensional mapping results have constrained various needs in people’s social life, coupled with the concept of digital city and advocacy, making three-dimensional, virtualization and actualization become the common pursuit of people’s goals. However, the original point cloud obtained is always incomplete due to reasons such as occlusion during acquisition and data density decreasing with distance, resulting in extracted boundaries that are often incomplete as well. In this paper, based on the study of current mainstream 3D model data organization methods, geographic grids and map service specifications, and other related technologies, an intelligent urban 3D modeling model based on multisource data point cloud algorithm is designed for the two problems of unified organization and expression of urban multisource 3D model data. A point cloud preprocessing process is also designed: point cloud noise reduction and downsampling to ensure the original point cloud geometry structure remain unchanged, while improving the point cloud quality and reducing the number of point clouds. By outputting to a common 3D format, the 3D model constructed in this paper can be applied to many fields such as urban planning and design, architectural landscape design, urban management, emergency disaster relief, environmental protection, and virtual tourism.

Since the development of 3D applications, the point cloud, as a spatial description easily acquired by sensors, has been widely used in multiple areas such as SLAM and 3D reconstruction. Point Cloud Compression (PCC) has also attracted more attention as a primary step before point cloud transferring and saving, where the geometry compression is an important component of PCC to compress the points geometrical structures. However, existing non-learning-based geometry compression methods are often limited by manually pre-defined compression rules. Though learning-based compression methods can significantly improve the algorithm performances by learning compression rules from data, they still have some defects. Voxel-based compression networks introduce precision errors due to the voxelized operations, while point-based methods may have relatively weak robustness and are mainly designed for sparse point clouds. In this work, we propose a novel learning-based point cloud compression framework named 3D Point Cloud Geometry Quantiation Compression Network (3QNet), which overcomes the robustness limitation of existing point-based methods and can handle dense points. By learning a codebook including common structural features from simple and sparse shapes, 3QNet can efficiently deal with multiple kinds of point clouds. According to experiments on object models, indoor scenes, and outdoor scans, 3QNet can achieve better compression performances than many representative methods.

Point cloud has emerged as the most popular three-dimensional (3D) data format in recent years for several scientific and industrial applications. Point cloud semantic segmentation has piqued the researcher’s interest, which is a crucial stage in 3D analysis and scene comprehension. Deep learning-based processing is more feasible to increase the availability of point cloud acquisition tools that is LiDAR systems at the user end. The point cloud learning achieves tremendous success in object detection, object categorization, and semantic segmentation. To summarize the recent works with chronological development, comprehensive review of projection-, voxel-, and direct point-based point cloud semantic segmentation methods is performed from various perspectives. The commonly used point cloud benchmark datasets with their characteristics are discussed, and they are used for the performance analysis and comparison of several state-of-the-art segmentation methods. The quantitative performance analysis of these deep learning models summarizes the trend of semantic segmentation of point clouds. In the context of point cloud semantic segmentation, the various methods have specific roles. Based on the review of methods working and their performance analysis, it is concluded that the projection-based methods prioritize efficiency, which is ideal in unavailability of high-performance computing system. Voxel-based methods capture overall context, serving well in 3D object classification. Point-based approaches excel in fine details and efficiency, suited for tasks like 3D semantic segmentation. Choosing the suitable method depends on the task, data, and resources. KPConv and DGCNN are popular choices, especially for precision and adaptability to point density. However, method performance varies, underlining the need for tailored selection. Hybrid approaches, combining method strengths, promise superior results.

The fusion of light detection and ranging (LiDAR) and camera provides comprehensive information about the depth and color texture of objects, finding wide applications in autonomous driving, three-dimensional (3D) scene reconstruction, and other fields. However, point clouds acquired via LiDAR are susceptible to noise, impacting downstream tasks like surface reconstruction and object recognition demanding high-quality point cloud outputs from 3D imaging systems. This paper proposes a novel 3D fusion imaging technique that enhances the quality of the fused point clouds from three distinct aspects, improving the accuracy and precision of point clouds by employing matched filter method, designing a preprocessing workflow for point clouds and images to enable their effective fusion, and smoothing noise and accentuating texture features using a filter algorithm on fused information. The method of matched filtering has been employed to reconstruct object distance information from photon count-time histograms, resulting in an improvement of approximately 120% compared to the method of directly calculating the average photon flight time. The point cloud filter proposed utilizing fused information demonstrates superior denoising capabilities compared to the state-of-the-art and has the capability to cluster points with similar features to highlight the texture characteristics of the point cloud.