UniPCGC: Towards Practical Point Cloud Geometry Compression via an Efficient Unified Approach

With the maturity of 3D capture technology, the explosive growth of point cloud data has burdened the storage and transmission process. Traditional hybrid point cloud compression (PCC) tools relying on handcrafted priors have limited compression performance and are increasingly weak in addressing the burden induced by data growth. Recently, deep learning-based PCC methods have been introduced to continue to push the PCC performance boundary. With the thriving of deep PCC, the community urgently demands a systematic overview to conclude the past progress and present future research directions. In this paper, we have a detailed review that covers popular point cloud datasets, algorithm evolution, benchmarking analysis, and future trends. Concretely, we first introduce several widely-used PCC datasets according to their major properties. Then the algorithm evolution of existing studies on deep PCC, including lossy ones and lossless ones proposed for various point cloud types, is reviewed. Apart from academic studies, we also investigate the development of relevant international standards (i.e., MPEG standards and JPEG standards). To help have an in-depth understanding of the advance of deep PCC, we select a representative set of methods and conduct extensive experiments on multiple datasets. Comprehensive benchmarking comparisons and analysis reveal the pros and cons of previous methods. Finally, based on the profound analysis, we highlight the challenges and future trends of deep learning-based PCC, paving the way for further study.

Efficient point cloud compression is essential for applications like virtual and mixed reality, autonomous driving, and cultural heritage. This paper proposes a deep learning-based inter-frame encoding scheme for dynamic point cloud geometry compression. We propose a lossy geometry compression scheme that predicts the latent representation of the current frame using the previous frame by employing a novel feature space inter-prediction network. The proposed network utilizes sparse convolutions with hierarchical multiscale 3D feature learning to encode the current frame using the previous frame. The proposed method introduces a novel predictor network for motion compensation in the feature domain to map the latent representation of the previous frame to the coordinates of the current frame to predict the current frame's feature embedding. The framework transmits the residual of the predicted features and the actual features by compressing them using a learned probabilistic factorized entropy model. At the receiver, the decoder hierarchically reconstructs the current frame by progressively rescaling the feature embedding. The proposed framework is compared to the state-of-the-art Video-based Point Cloud Compression (V-PCC) and Geometry-based Point Cloud Compression (G-PCC) schemes standardized by the Moving Picture Experts Group (MPEG). The proposed method achieves more than 88% BD-Rate (Bjøntegaard Delta Rate) reduction against G-PCCv20 Octree, more than 56% BD-Rate savings against G-PCCv20 Trisoup, more than 62% BD-Rate reduction against V-PCC intra-frame encoding mode, and more than 52% BD-Rate savings against V-PCC P-frame-based inter-frame encoding mode using HEVC. These significant performance gains are cross-checked and verified in the MPEG working group.

Existing methods of unstructured point cloud compression usually exploit the spatial sparseness of point clouds using hierarchical tree data structures for spatial encoding. However, such methods can be inefficient when very deep octrees are applied to sparse point cloud data to maintain low level of geometric error during compression. This paper proposes a novel octree structure called truncated octree that improves the compression ratio by representing the deep octree with a set of shallow sub-octrees which can save storage without losing the original structure. We also propose a variable length addressing scheme, to adaptively choose the length of an octree’s node address based on the truncation level—shorter (resp. longer) address when octree is truncated near the leaf (resp. root) which leads to further compression. The method is able to achieve 40% to 90% compression ratio on our tested models for point clouds of different spatial distributions. For extremely sparse point clouds, the method achieves approximately 7 times higher compression ratio than previous methods. Moreover, the method is designed to run in parallel for octree construction, encoding and decoding.

We use both lossy and lossless compression methods to reduce large amounts of digital data, making it easier to store and manage. Lossy and lossless compression is frequently used in astronomy, to condense the large amount of data collected by instruments namely, the James Webb Space Telescope and the Hubble Space Telescope. Similarly to diffraction images, astronomical images have large areas of empty space since stellar objects are very bright, yet show very small in images, which after a while, takes up a needless amount of limited digital storage space. Lossy compression achieves higher compression ratios but sacrifices some data quality in the process, while lossless compression preserves the data’s original form, but results in less storage savings. This work, conducted at Brookhaven National Laboratory’s National Synchrotron Light Source-II at the AMX and FMX macromolecular beam lines, aimed to evaluate the effectiveness of the lossy compression method known as Wavelet Compression. Wavelet compression is a method of data compression that uses wavelet transforms to reduce the size of data while preserving its essential features. Crystals are repetitive molecular assemblies that create diffraction patterns when exposed to X-rays, while detectors capture the amplitude of diffraction pattern spots (reflections). Similar to astronomical images, diffraction images contain large areas of empty space. This unnecessary data can quickly consume limited digital storage. By studying and optimizing compression methods, we not only improve data management but also advancements in various scientific disciplines.

Compression of computed tomography (CT) projection samples reduces slip ring and disk drive costs. A lowcomplexity, CT-optimized compression algorithm called Prism CT^TM achieves at least 1.59:1 and up to 2.75:1 lossless compression on twenty-six CT projection data sets. We compare the lossless compression performance of Prism CT to alternative lossless coders, including Lempel-Ziv, Golomb-Rice, and Huffman coders using representative CT data sets. Prism CT provides the best mean lossless compression ratio of 1.95:1 on the representative data set. Prism CT compression can be integrated into existing slip rings using a single FPGA. Prism CT decompression operates at 100 Msamp/sec using one core of a dual-core Xeon CPU. We describe a methodology to evaluate the effects of lossy compression on image quality to achieve even higher compression ratios. We conclude that lossless compression of raw CT signals provides significant cost savings and performance improvements for slip rings and disk drive subsystems in all CT machines. Lossy compression should be considered in future CT data acquisition subsystems because it provides even more system benefits above lossless compression while achieving transparent diagnostic image quality. This result is demonstrated on a limited dataset using appropriately selected compression ratios and an experienced radiologist.

In this paper, we evaluate lossless and lossy compression techniques to compress quantitative phase images of red blood cells (RBCs) obtained by an off-axis digital holographic microscopy (DHM). The RBC phase images are numerically reconstructed from their digital holograms and are stored in 16-bit unsigned integer format. In the case of lossless compression, predictive coding of JPEG lossless (JPEG-LS), JPEG2000, and JP3D are evaluated, and compression ratio (CR) and complexity (compression time) are compared against each other. It turns out that JP2k can outperform other methods by having the best CR. In the lossy case, JP2k and JP3D with different CRs are examined. Because some data is lost in a lossy way, the degradation level is measured by comparing different morphological and biochemical parameters of RBC before and after compression. Morphological parameters are volume, surface area, RBC diameter, sphericity index, and the biochemical cell parameter is mean corpuscular hemoglobin (MCH). Experimental results show that JP2k outperforms JP3D not only in terms of mean square error (MSE) when CR increases, but also in compression time in the lossy compression way. In addition, our compression results with both algorithms demonstrate that with high CR values the three-dimensional profile of RBC can be preserved and morphological and biochemical parameters can still be within the range of reported values.

Lossy compressors are increasingly adopted in scientific research, tackling volumes of data from experiments or parallel numerical simulations and facilitating data storage and movement. In contrast with the notion of entropy in lossless compression, no theoretical or data-based quantification of lossy compressibility exists for scientific data. Users rely on trial and error to assess lossy compression performance. As a strong data-driven effort toward quantifying lossy compressibility of scientific datasets, we provide a statistical framework to predict compression ratios of lossy compressors. Our method is a two-step framework where (i) compressor-agnostic predictors are computed and (ii) statistical prediction models relying on these predictors are trained on observed compression ratios. Proposed predictors exploit spatial correlations and notions of entropy and lossyness via the quantized entropy. We study 8+ compressors on 6 scientific datasets and achieve a median percentage prediction error less than 12%, which is substantially smaller than that of other methods while achieving at least a 8.8× speedup for searching for a specific compression ratio and 7.8× speedup for determining the best compressor out of a collection.

Image compression is the application of data compression techniques to two-dimensional digital images I(x, y) , to reduce the redundancy of the image data for storage or transmission in an efficient form. Image compression can be classified into two categories: lossless or lossy. Lossless compression, which achieves smaller compression ratios than lossy compression, mainly takes advantage of the image contents containing a non uniform probability distribution for a variable-length representation of the image pixels. Such images include technical drawings, icons or comics, and high-value contents such as medical imagery or image scans made for archival purposes. However, lossy compression methods, especially when they achieve a very high compression ratio, can introduce compression artifacts. Nevertheless, lossy compressions are especially suitable for natural images, such as photos, in applications where a minor (sometimes imperceptible) loss of fidelity is acceptable when it is desirable to achieve a substantial reduction in bitrate. Most of the stateof-the-art image compression standards use a combination of lossy and lossless algorithms to achieve the best performance. The Joint Photographic Experts Group (JPEG) [1], a discrete cosine transform(DCT)-based technique, is the most widely used standardized lossy image compression mechanism; it was designed for compressing either full-color or gray-scale images of natural, real-world, scenes. It works well for photographs, naturalistic artwork and similar material if the compression ratio is about 20 : 1, which is much better than the 4 : 1 compression ratio provided by a lossless compression method such as the Graphics Interchange Format (GIF) [2]. However, it does not work so well for lettering, simple cartoons, or line drawings.

Converting three-dimensional (3D) point cloud data to two-dimensional (2D) image based on virtual structured-light system is a popular method in 3D data compression because the image format is easier to process by the exiting storing and transmitting methods. When this method is used in the 3D point cloud compression, the quantization error is introduced during the coordinate mapping. To solve this problem, a virtual structured-light 3D point cloud compression algorithm based on geometric reshaping is presented. And a least-square system parameter optimization method is proposed to further improve the data decoding accuracy. In the proposed method, the 3D spatial coordinates are reshaped to a 2D matrix first, and then the 2D matrix is stored as a “Holoimage” by using the parameter optimized virtual structured-light system. The quantization error introduced by coordinate mapping between X and Y coordinates of the 3D point cloud and the 2D image pixel coordinates is suppressed, so the decoding accuracy is improved. In addition, the geometric information of the 3D point cloud is hidden synchronously when the 3D point cloud is compressed, which is of great significance in the copyright protection of the point cloud data. Experiments verify the effectiveness of the proposed algorithm. The decoding root mean square error (RMSE) of the proposed method is decreased by 79.86% on average compared with the traditional one under the same compression ratio, and the compression ratio of the proposed method is 1.96 times bigger than the traditional one under the similar decoding accuracy.

Modern laser scanners, depth sensor devices and Dense Image Matching techniques allow for capturing of extensive point cloud datasets. While capturing has become more user-friendly, the size of registered point clouds results in large datasets which pose challenges for processing, storage and visualization. This paper presents a decomposition scheme using oriented KD trees and the wavelet transform for unordered point clouds. Taking inspiration from image pyramids, the decomposition scheme comes with a Level of Detail representation where higher-levels are progressively reconstructed from lower ones, thus making it suitable for streaming and continuous Level of Detail. Furthermore, the decomposed representation allows common compression techniques to achieve higher compression ratios by modifying the underlying frequency data at the cost of geometric accuracy and therefore allows for flexible lossy compression. After introducing this novel decomposition scheme, results are discussed to show how it deals with data captured from different sources.

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.

Light source facilities, which generate X-rays for probing microstructures and dynamic processes, produce intense data streams, reaching up to 250 GB/s and projected to exceed 1 TB/s by the end of this decade. Managing such massive data poses critical challenges due to limited local processing capacity and bandwidth constraints when offloading data to HPC systems. To address these challenges, we propose lsCOMP, a GPU compressor that operates within a single kernel. lsCOMP supports both lossless and configurable lossy compression, ensuring high compression ratios and preserved data quality across diverse light source applications. On a single NVIDIA A100 GPU, lsCOMP achieves compression throughputs of 380.89 to 509.21 GB/s in lossless mode, delivering up to 20 times higher performance than industry-leading GPU compressors while achieving superior compression ratios. In lossy modes, lsCOMP further improves throughput and ratios significantly. Additionally, lsCOMP demonstrates versatile performance across various integer datasets and supports TB/s-level random access throughput.

3D point cloud presentation has been widely used in computer vision, automatic driving, augmented reality, smart cities and virtual reality. 3D point cloud compression method with higher compression ratio and tiny loss is the key to improve data transportation efficiency. In this paper, we propose a new 3D point cloud geometry compression method based on deep learning, also an auto-encoder performing better than other networks in detail reconstruction. It can reach much higher compression ratio than the state-of-art while keeping tolerable loss. It also supports parallel compressing multiple models by GPU, which can improve processing efficiency greatly. The compression process is composed of two parts. Firstly, Raw data is compressed into codeword by extracting feature of raw model with encoder. Then, the codeword is further compressed with sparse coding. Decompression process is implemented in reverse order. Codeword is recovered and fed into decoder to reconstruct point cloud. Detail reconstruction ability is improved by a hierarchical structure in our decoder. Latter outputs are grown from former fuzzier outputs. In this way, details are added to former output by latter layers step by step to make a more precise prediction. We compare our method with PCL compression and Draco compression on ShapeNet40 part dataset. Our method may be the first deep learning-based point cloud compression algorithm. The experiments demonstrate it is superior to former common compression algorithms with large compression ratio, which can also reserve original shapes with tiny loss.

Point cloud compression (PCC) is crucial for efficient and flexible storage as well as feasible transmission of point clouds in practice. For geometry compression, one popular approach is the octree-based solution. The intra prediction mechanism utilizes the spatial correlation in the static point cloud to predict the occupancy bit of the octree node for entropy coding, reducing the spatial redundancy. In this study, two local geometry-based prediction methods are proposed following statistical and theoretical analyses: binary prediction, which outputs the binary state (i.e., occupied or unoccupied), and ternary prediction, which provides a third option other than occupied or unoccupied (i.e., not predicted). In comparison to the state-of-the-art, the proposed binary prediction offers the Bjontegaard delta rate (BD-rate) of −0.8% for lossy compression and the bits per input point (bpip) of 100.09% for lossless compression in average, respectively. The binary prediction reduces the computational complexity in terms of more than 20% decrease in decoding time. In particular, it also provides noticeable reduction of the memory usage during entropy coding. The proposed ternary prediction provides −1.2% BD-rate for lossy compression and 97.19% bpip for lossless compression in average, respectively, in comparison to the state-of-the-art. While achieving performance gain, it is considerably more computational efficient by saving about 18% decoding time. Due to these advantages, part of the proposed ternary prediction has been adopted by the ongoing MPEG standard of geometry-based point cloud compression (G-PCC).

Microarray image compression: SLOCO and the effect of information loss