In this paper, we propose a deep hierarchical attention context model for lossless attribute compression of point clouds, leveraging a multi-resolution spatial structure and residual learning. A simple and effective Level of Detail (LoD) structure is introduced to yield a coarse-to-fine representation. To enhance efficiency, points within the same refinement level are encoded in parallel, sharing a common context point group. By hierarchically aggregating information from neighboring points, our attention model learns contextual dependencies across varying scales and densities, enabling comprehensive feature extraction. We also adopt normalization for position coordinates and attributes to achieve scale-invariant compression. Additionally, we segment the point cloud into multiple slices to facilitate parallel processing, further optimizing time complexity. Experimental results demonstrate that the proposed method offers better coding performance than the latest G-PCC for color and reflectance attributes while maintaining more efficient encoding and decoding run-times.

Point cloud attribute compression is a challenging issue in efficiently compressing large volumes of attributes. Despite notable advancements in lossy point cloud compression using deep learning, progress in lossless compression remains limited. Some methods have employed octree- or voxel-based partitioning techniques derived from geometric compression, achieving success on dense point clouds. However, these voxel-based approaches struggle with sparse or unevenly distributed point clouds, leading to performance degradation. In this work, we introduce a novel framework for learning-based lossless point cloud attribute compression, named LOD-PCAC, which leverages a Level-of-Detail (LOD) structure to ensure density-robust compression. Specifically, the input point cloud is divided into multiple detail levels, and vertices from these levels are selected to construct a Reference Set as context, which effectively captures multi-level information. Then we propose the Bit-level Residual Coder for efficient attribute compression. Instead of directly compressing attributes, our method first predicts attribute values and organizes the residual bits into a Bit Matrix as another context, simplifying predictions and fully exploiting channel correlations. Finally, a neural network with specialized encoders processes the context to estimate the probability of each residual bit. Experimental results demonstrate that the proposed method outperforms both traditional and learning-based approaches across various point clouds, exhibiting strong generalization across datasets and robustness to varying densities.

The Geometry-based Point Cloud Compression (G-PCC) has been developed by the Moving Picture Experts Group to compress point clouds efficiently. Nevertheless, in its lossy mode, the reconstructed point cloud by G-PCC often suffers from noticeable distortions due to naïve geometry quantization (i.e., grid downsampling). This paper proposes a hierarchical prior-based super resolution method for point cloud geometry compression. The content-dependent hierarchical prior is constructed at the encoder side, which enables coarse-to-fine super resolution of the point cloud geometry at the decoder side. A more accurate prior generally yields improved reconstruction performance, albeit at the cost of increased bits required to encode this piece of side information. Our experiments on the MPEG Cat1A dataset demonstrate substantial Bjøntegaard-delta bitrate savings, surpassing the performance of the octree-based and trisoup-based G-PCC v14. We provide our implementations for reproducible research at https://github.com/lidq92/mpeg-pcc-tmc13.

Point cloud is an informative type of media to represent objects and scenes. Along with the geometry information that records the 3D shapes, multiple types of attribute information can be included to characterize the visual appearance of objects and scenes. To deal with the massive data volume of point clouds, developing compression algorithms is necessary. While various prediction techniques have been proposed to reduce the information redundancy for individual point cloud attribute, the correlation between different types of attribute is, however, not fully investigated. This paper first studies the correlation between different types of attribute. A cross-type attribute prediction method is then proposed. The proposed method is evaluated on top of different point cloud compression frameworks with various point cloud sequences. Experimental results show that the proposed cross-type attribute prediction method is able to significantly improve the coding efficiency with marginal coding complexity.

In this paper, a new predictive wavelet transform (PWT) is proposed to solve LiDAR point clouds attribute compression. Our method is a combination of predictive coding and Haar wavelet transform. Based on the spatial information, a hierarchical predictive transform tree is designed to represent 3D irregular data points efficiently. Each level node is classified as a predictive node (P-node) or a transform node (T-node) according to the distances to its adjacent nodes. Then in a top-down coding process, the Haar transform is applied to all T-node pairs, and predictive coding is processed on all P-nodes alternately. It is shown by experimental results that the proposed PWT method offers better R-D performances compared with state-of-the-art methods.

Point cloud compression (PCC) is a crucial enabler for immersive multimedia applications since point cloud is one of the most primitive forms for representing 3D scenes and objects. Recently, some approaches are proposed to improve the average reconstruction quality of octree-based Geometry-based Point Cloud Compression (G-PCC). However, it is noticed that these approaches suffer considerable loss in terms of point-to-point (D1) Hausdorff distance when compared to G-PCC (octree). Here we introduce a near-lossless point cloud geometry compression method based on adaptive residual compensation by adding and removing points with large errors. It allows controlling of D1 Hausdorff (D1h) distance and maintains a great improvement in average reconstruction performance over G-PCC. Experimental results verify the effectiveness of our method, where our method achieves an average of 78.5% D1 and 11.4% D1h Bjontegaard-delta bitrate savings over the octree-based G-PCC on solid point clouds of the MPEG Cat1A dataset.

Though recent advances in point cloud completion have shown exciting promise with learning-based methods, most of them still generate coarse point clouds with a fixed number of points (e.g. 2048). In this paper, we propose Vaccine-Style-Net, a new point cloud completion method that can produce high resolution 3D shapes with complete smooth surface. Vaccine-Style-Net performs point cloud completion in the function space of 3D surface, which represent the 3D surface as the continuous decision boundary function. Meanwhile, a reinforcement learning agent is embedded to deduce the complete 3D geometry from the incomplete point cloud. In contrast to the existing approaches, the completed 3D shapes produced by our method can be any resolution without excessive memory footprint. Moreover, to increase the diversity and adaptability of the method, we introduce two-type-free-form masks to simulate various corrupted inputs as well as a mask dataset called onion-peeling-mask (OPM). Finally, we discuss the limitations of existing evaluation metrics for shape completion tasks and explore a novel metric to supplement the existing ones. Experiments demonstrate that our method not only achieves competitive results qualitatively and quantitatively but also can produce a continuous 3D shape with any resolution.

Inspired by the recently proposed successive subspace learning (SSL) principles, we develop a successive subspace graph transform (SSGT) to address point cloud attribute compression in this work. The octree geometry structure is utilized to partition the point cloud, where every node of the octree represents a point cloud subspace with a certain spatial size. We design a weighted graph with self-loop to describe the subspace and define a graph Fourier transform based on the normalized graph Laplacian. The transforms are applied to large point clouds from the leaf nodes to the root node of the octree recursively, while the represented subspace is expanded from the smallest one to the whole point cloud successively. It is shown by experimental results that the proposed SSGT method offers better R-D performances than the previous Region Adaptive Haar Transform (RAHT) method.

In this paper, we propose a sphere-projection-based framework for point cloud geometry and attribute lossless and lossy coding. The original point cloud is adaptively divided into blocks, and then we create a fitting sphere in each block for modeling the local geometry structure of the point cloud. Sphere coordination transform and spherical projection scheme are introduced to transfer a 3D point cloud to a set of the range images. A novel compact representation of generated range images based on Morton codes is proposed to separate the range images into occupancy images and attributes vectors for further compression. Experimental results demonstrate that for the LiDAR point clouds datasets in lossless compression, the proposed method offers better performance than geometry-based point cloud compression (G-PCC). For the object point clouds datasets in lossy compression, the proposed method has better rate-distortion (R-D) performance than Draco.

Due to the emerging requirement of point cloud applications, efficient point cloud compression methods are in high demand for compact point cloud representation in limited bandwidth transmission. The compression standard GPCC (Geometry-based Point Cloud Compression) is led by the MPEG (Moving Picture Expert Group) in respond to industrial requirements. KNN (K-Nearest Neighbors) search based prediction method is adopted for point cloud attribute compression in current G-PCC, which only exploits Euclidean distance-based geometric relationship without fully consideration of underlying geometric distribution. In this paper, we propose a novel prediction scheme based on fast recolor technique for attribute lossless and near-lossless compression. Our method has been implemented upon G-PCC reference software of the latest version. Experimental results show that our method can take advantage of the correlation between the attributes of neighbors, which leads to better rate-distortion (R-D) performance than G-PCC anchor on point cloud dataset with negligible encode and decode time increase under the common test conditions.

3D point cloud compression (PCC) has been an attractive field with increasing applications in recent years. Moving Picture Experts Group (MPEG) is building an open standard for point cloud compression, consisting of two solutions, video-based point cloud compression (V-PCC) and geometry-based point cloud compression (G-PCC). As an essential process in G-PCC, K-nearest neighbors (KNN) algorithm is adopted to perform intra prediction, which only considering distance-based local similarity but neglecting the overall geometric distribution of the neighbor set. In this paper, we propose an enhanced intra prediction scheme based on point-cloud geometric distribution. The centroid-based criterion is introduced to measure the uniformity of spatial distribution of predictive reference points. Our scheme is implemented in G-PCC reference software. Experimental results demonstrate that our proposed method can optimize the selection of predictors, which leads to better rate-distortion (R-D) performance than the G-PCC anchor on point cloud datasets under the common test conditions (CTC).