Multi-grained point cloud geometry compression via dual-model prediction with extended octree

T Qin, G Li, W Gao, S Liu - ACM Transactions on Multimedia Computing …, 2024 - dl.acm.org
The state-of-the-art geometry-based point cloud compression (G-PCC)(Octree) is the fine-
grained approach, which uses the octree to partition point clouds into voxels and predicts …

IPDAE: Improved patch-based deep autoencoder for lossy point cloud geometry compression

K You, P Gao, Q Li - Proceedings of the 1st International Workshop on …, 2022 - dl.acm.org
Point cloud is a crucial representation of 3D contents, which has been widely used in many
areas such as virtual reality, mixed reality, autonomous driving, etc. With the boost of the …

Non-rigid registration-based progressive motion compensation for point cloud geometry compression

Y Shao, G Li, Q Zhang, W Gao… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
There is a critical requirement for efficiently compressing point cloud geometries
representing 3-D moving objects in various applications. The Moving Picture Experts Group …

Multiscale latent-guided entropy model for lidar point cloud compression

T Fan, L Gao, Y Xu, D Wang, Z Li - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
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 …

Efficient lidar point cloud geometry compression through neighborhood point attention

R Xue, J Wang, Z Ma - arxiv preprint arxiv:2208.12573, 2022 - arxiv.org
Although convolutional representation of multiscale sparse tensor demonstrated its superior
efficiency to accurately model the occupancy probability for the compression of geometry …

Isolated points prediction via deep neural network on point cloud lossless geometry compression

Z Wei, B Niu, H **ao, Y He - … on Circuits and Systems for Video …, 2022 - ieeexplore.ieee.org
The point cloud is one of the indispensable data structures of virtual and mixed reality
applications. Vivid scene requirement means that millions of points need to be encoded …

Pcgformer: Lossy point cloud geometry compression via local self-attention

G Liu, J Wang, D Ding, Z Ma - 2022 IEEE International …, 2022 - ieeexplore.ieee.org
Although the multiscale sparse tensor using stacked convolutions has attained noticeable
gains for lossy compression of point cloud geometry (PCG), its capability suffers because …

Geometric Prior Based Deep Human Point Cloud Geometry Compression

X Wu, P Zhang, M Wang, P Chen… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
The emergence of digital avatars has prompted an exponential increase in the demand for
human point clouds with realistic and intricate details. The compression of such data …

[HTML][HTML] Neighborhood constraint extraction for rapid modeling of point cloud scenes in large-scale power grid substations

R Li, L Gan, Y Di, H Tian, Q Zuo, Y Luo, X Wu… - Journal of King Saud …, 2024 - Elsevier
Abstract 3D laser scanning is widely used in modeling industrial scenes, involving crucial
steps like point cloud (PC) data preprocessing and extracting modeling targets from …

Learning Hierarchical Adaptive Code Clouds for Neural 3D Shape Representation

Y Lu, X Ji, H Zhu, X Cao - Machine Intelligence Research, 2025 - Springer
Neural implicit representation (NIR) has attracted significant attention in 3D shape
representation for its efficiency, generalizability, and flexibility compared with traditional …