We propose a novel deep lossless geometry compression algorithm for triangle mesh. Typical traditional triangle mesh compression algorithms are connectivity-driven, which first codes connectivity and then codes vertices according to the encoded connectivity. However, vertex compression is inefficient since these algorithms lack the exploitation of vertices' intra-component redundancy, which point cloud compression (PCC) excels at. Therefore, our approach first compresses the vertices with a lossless PCC algorithm since the vertices could be considered as a point cloud. Moreover, based on the encoded vertices, the bitrate of connectivity could be decreased further by exploiting the cross-component redundancy between vertex and connectivity. Specifically, we divide the connectivity into KNN connectivity and isolated connectivity. We design a deep entropy model for KNN connectivity compression. This model extracts the spatial feature of encoded vertices first, then predicts the vertex-pairs' connection probabilities using the spatial feature. In order to exploit the intra-component redundancy, an auto-regressive strategy is also employed when predicting. The predicted probabilities are finally fed into a binary arithmetic coder to code the KNN connectivity into a compact bitstream. The isolated connectivity is encoded in direct coding mode (DCM). To our knowledge, this paper is the first work to utilize the deep neural network on mesh compression. We validate the effectiveness of our method on simplified MPEG V-DMC dataset. Experimental results demonstrate that the proposed method achieves average 7.33% and 40.75% bpv gains on connectivity and vertex separately, resulting average 30.26% bpv gains on total mesh compression compared with MPEG SC3DMC.

The non-uniform distribution and extremely sparse nature of the LiDAR point cloud (LPC) bring significant challenges to its high-efficient compression. This paper proposes a novel end-to-end, fully-factorized deep framework that represents the original LiDAR point cloud into an octree structure and hierarchically constructs the octree entropy model in layers. The proposed framework utilizes a hierarchical latent variable as side information to encapsulate the sibling and ancestor dependence, which provides sufficient context information for the modeling of point cloud distribution while enabling the parallel encoding and decoding of octree nodes in the same layer. Besides, we propose a residual coding framework for the compression of the latent variable, which explores the spatial correlation of each layer by progressive downsampling, and model the corresponding residual with a fully-factorized entropy model. Furthermore, we propose soft addition and subtraction for residual coding to improve network flexibility. The comprehensive experiment results on the LiDAR benchmark SemanticKITTI and MPEG-specified dataset Ford demonstrate that our proposed framework achieves state-of-the-art performance among all the previous LPC frameworks. Besides, our end-to-end, fully-factorized framework is proved by experiment to be high-parallelized and time-efficient, which saves more than 99.8% of decoding time compared to previous state-of-the-art methods on LPC compression.

The non-uniformly distributed nature of the 3D Dynamic Point Cloud (DPC) brings significant challenges to its high-efficient inter-frame compression. This paper proposes a novel 3D sparse convolution-based Deep Dynamic Point Cloud Compression (D-DPCC) network to compensate and compress the DPC geometry with 3D motion estimation and motion compensation in the feature space. In the proposed D-DPCC network, we design a Multi-scale Motion Fusion (MMF) module to accurately estimate the 3D optical flow between the feature representations of adjacent point cloud frames. Specifically, we utilize a 3D sparse convolution-based encoder to obtain the latent representation for motion estimation in the feature space and introduce the proposed MMF module for fused 3D motion embedding. Besides, for motion compensation, we propose a 3D Adaptively Weighted Interpolation (3DAWI) algorithm with a penalty coefficient to adaptively decrease the impact of distant neighbours. We compress the motion embedding and the residual with a lossy autoencoder-based network. To our knowledge, this paper is the first work proposing an end-to-end deep dynamic point cloud compression framework. The experimental result shows that the proposed D-DPCC framework achieves an average 76% BD-Rate (Bjontegaard Delta Rate) gains against state-of-the-art Video-based Point Cloud Compression (V-PCC) v13 in inter mode.

The attached attributes of each point in point cloud are fairly valuable but aggravate the burden for storage and transmission. In this paper, we propose a learning-based intra-prediction method for region adaptive hierarchical transform (RAHT) to compress point cloud attributes efficiently. First, we design an adaptive neighbor selection (ANS) module to produce the most correlated neighbors for child nodes. Then, the correlated neighbors obtained by ANS, the corresponding distance weights, and some additional auxiliary information are concatenated and fed to a multi-layer perception (MLP) based network to estimate the child node attributes precisely. Besides, residual learning is introduced to accelerate the network convergence. The predicted child node attributes are finally transformed by RAHT, and the residual of transform coefficients are then quantized and entropy coded. Experimental results demonstrate that our proposed methods can significantly improve attribute coding efficiency with average 10.2% BD-Rate gains compared with MPEG G-PCC reference software TMC13v14.0 on MPEG PCC dataset.

Compressing point cloud geometry (PCG) efficiently is of great interests for enabling abundant networked applications, because PCG is a promising representation to precisely illustrate arbitrary-shaped 3D objects and relevant physical scenes. To well exploit the unconstrained geometric correlation of input PCG, a three-step neural graph sampling (NGS) is developed. First, we construct the local graph of each point using its K nearest neighbors according to the Euclidean distance metric; Second, for each local graph, its graph center point expands associated feature attribute by aggregating neighbor weights via point-wise dynamic filter; We then perform attention-based sampling to select a subset of points to well represent input points. The proposed NGS is embedded into an end-to-end analysis/synthesis-based variational autoencoder (VAE), with which the encoder applies multiscale NGS to extract latent keypoints that are augmented with neighbor structures and compressed at bottleneck leveraging the hyperpriors for accurate entropy modeling, and the decoder directly uses layered convolutions to refine progressively for the reconstruction of final point cloud. Note that all computations are fulfilled using point-wise convolution, making our solution an attractive approach in practice. Experimental results demonstrate that the proposed method using NGS mechanism outperforms the state-of-the-art point-based PCG compression methods by more than $2\times \mathrm{B}\mathrm{D}$-Rate (Bjûntegaard Delta Rate) gains, and several orders of magnitude gains over the MPEG G-PCC across all testing categories on ShapeNetCorev2 dataset.