3QNet

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.

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.

In this paper, we propose a reduced reference (RR) point cloud quality assessment (PCQA) model named R-PCQA to quantify the distortions introduced by the lossy compression. Specifically, we use the attribute and geometry quantization steps of different compression methods (i.e., V-PCC, G-PCC and AVS) to infer the point cloud quality, assuming that the point clouds have no other distortions before compression. First, we analyze the compression distortion of point clouds under separate attribute compression and geometry compression to avoid their mutual masking, for which we consider 5 point clouds as references to generate a compression dataset (PCCQA) containing independent attribute compression and geometry compression samples. Then, we develop the proposed R-PCQA via fitting the relationship between the quantization steps and the perceptual quality. We evaluate the performance of R-PCQA on both the established dataset and another independent dataset. The results demonstrate that the proposed R-PCQA can exhibit reliable performance and high generalization ability.

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.

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.

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.

Point cloud compression has been studied in standard bodies and we are here concerned with the Moving Picture Experts Group video-based point cloud compression (V-PCC) solution. Plenoptic point clouds (PPC) is a novel volumetric data representation wherein points are associated with colors in all viewing directions to improve realism. It is sampled as a number ( Nc ) of attribute colors per point. We propose a new method for the efficient video-based compression of PPC that is backwards compatible with the existing single-color V-PCC decoder. V-PCC generates three image atlases which are encoded using an image/video encoder. We assume there may be a reference color which is to be encoded as the main payload. We generate Nc+3 atlases and we produce Nc differential images against the reference color image. Those difference images are pixel-wise transformed using an Nc -point discrete cosine transform, generating Nc transformed atlases which are encoded, forming the secondary payload. Such secondary information is the plenoptic enhancement to the point cloud. If there is no reference attribute, we skip the differences and use the lowest frequency of the transformed atlases as the main payload. Results are presented that show an unrivaled performance of the proposed method.

Point cloud compression is essential for the efficient storage and transmission of 3D data in various applications, such as virtual reality, autonomous driving, and 3D modelling. Most existing compression methods employ voxelisation, all of which uniformly partition 3D space into voxels for more efficient compression. However, uniform voxelisation may not capture the underlying geometry of complex scenes effectively. In this paper, we propose a novel non-uniform voxelisation technique for point cloud geometry compression. Our method adaptively adjusts voxel sizes based on local point density, preserving geometric details while enabling more accurate reconstructions. Through comprehensive experiments on the well-known benchmark datasets ScanNet, ModelNet and ShapeNet, we demonstrate that our approach achieves better compression ratios and reconstruction quality in comparison to traditional uniform voxelisation methods. The results highlight the potential of non-uniform voxelisation as a viable and effective alternative, offering improved performance for point cloud geometry compression in a wide range of real-world scenarios.

Video-based point cloud compression (V-PCC) has achieved remarkable performance in dynamic point cloud compression. However, due to the 3D-to-2D projection in V-PCC, the temporal continuity across projected video frames is broken, limiting inter-frame coding efficiency. In this paper, we propose a virtual reference-based predictive coding (VRPC) scheme for V-PCC attribute compression to improve coding efficiency. This coding scheme uses the temporal correspondence between point clouds to guide the alignment of attribute video frames for virtual reference frame generation. Specifically, we first construct a neural deformation field-based geometry alignment module to align the reference and target point clouds to reduce the effect of motion on temporal correspondence estimation. Then, temporal correspondence is obtained in 3D space and used to align the reference and target video frames to generate the occupied region of the virtual reference frame. Finally, after padding the unoccupied region, the resulting reference frame is added to the reference picture list and used by the target frame for inter-frame coding. Experimental results demonstrate that the proposed method effectively improves the attribute coding efficiency of V-PCC.

With the development of computer vision technologies, 3D reconstruction has become a hotspot. At present, 3D reconstruction relies heavily on expensive equipment and has poor real-time performance. In this paper, we aim at solving the problem of 3D reconstruction of an indoor scene with large vertical span. In this paper, we propose a novel approach for 3D reconstruction of indoor scenes with only a Kinect. Firstly, this method uses a Kinect sensor to get color images and depth images of an indoor scene. Secondly, the combination of scale-invariant feature transform and random sample consensus algorithm is used to determine the transformation matrix of adjacent frames, which can be seen as the initial value of iterative closest point (ICP). Thirdly, we establish the relative coordinate relation between pair-wise frames which are the initial point cloud data by using ICP. Finally, we achieve the 3D visual reconstruction model of indoor scene by the top-down image registration of point cloud data. This approach not only mitigates the sensor perspective restriction and achieves the indoor scene reconstruction of large vertical span, but also develops the fast algorithm of indoor scene reconstruction with large amount of cloud data. The experimental results show that the proposed algorithm has better accuracy, better reconstruction effect, and less running time for point cloud registration. In addition, the proposed method has great potential applied to 3D simultaneous location and mapping.

The dynamic point cloud is widely needed in 3D vision related applications such as virtual reality and telepresence. Due to the huge amount of data, a key technology before the effective application is the dynamic point cloud compression. The state-of-the-art dynamic point cloud compression scheme, video-based point cloud compression (V-PCC), generates 2D videos with some uncorrelation due to the patch segmentation and packing process, which will affect the compression efficiency. In this paper, we propose a Packing with Patch Correlation Improvement (PPCI) algorithm to adaptively remove the uncorrelated parts between matched patches in packing for the sake of inter-prediction performance. We first propose a basic unidirectional patch re-segmentation operator to remove the uncorrelated parts of the patches in the current point cloud relative to the patches in its reference point cloud. The removed parts will be formed as new patches and added to the patch collection of the current point cloud. Then we propose a back-and-forth structure, which is a combination of several basic patch re-segmentation operators, to bilaterally remove the uncorrelated parts of matched patches in a back-and-forth (BF) unit. Furthermore, we propose a framework to adaptively decide the best length of each BF unit in a point cloud sequence. Experimental results show that our method achieves noticeable bitrate savings compared with the existing V-PCC packing methods, particularly for sequences with small motion.

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).

Completing point clouds using structural constraints for large-scale points absence in 3D building reconstruction

In Amazon Robotic Challenge, we need to make unknown object's 3d model for recognizing and estimating 6D pose in limited time. The paper presents a unique autonomous system to build object's complete 3d model fast. This method is different with others for it can build object's model contains object's bottom side. We modify ElasticFusion to focus on building object's 3D model from object's up-side with assistant pose information from Aruco Markers. Then instead of using ICP or other merge algorithms, we merge object's upside point cloud and bottom-side point cloud easily by using Aruco Markers on transparent board. At last, we use octree and source point cloud to color poisson reconstruction mesh model to obtain object's final complete colored 3d model. Experiment results show that our approach can generate common object's complete model with acceptable size error in limited time.

With the rapid development of 3D sensing and reconstruction technologies, point cloud compression has become an active research area. When designing compression methods for point cloud attributes, the reconstructed geometry information is commonly used to guide the attribute compression. Specifically, the geometric distance between points is widely applied in different forms to assist attribute prediction. However, due to the complicated spatial distributions of 3D point clouds, using distance as the sole feature may not be optimal. In this paper, the spatial distribution of point clouds is further considered to derive a distribution-driven attribute pre-diction. Experimental results show that the proposed method can significantly improve the coding efficiency of G-PCC. The proposed method has been adopted in the technologies under consideration (TuC) for MPEG G-PCC and will be included in the second version of the G-PCC specification.