PVContext: Hybrid Context Model for Point Cloud Compression
This work addresses storage challenges for large-scale point cloud data, offering significant compression gains for applications like LiDAR scanning and 3D object representation, though it is incremental as it builds on existing deep learning and octree-based methods.
The paper tackles the problem of efficient point cloud compression by proposing PVContext, a hybrid context model that integrates voxel and point contexts to capture both local and global information, achieving bitrate reductions of up to 48.98% compared to G-PCC on various datasets.
Efficient storage of large-scale point cloud data has become increasingly challenging due to advancements in scanning technology. Recent deep learning techniques have revolutionized this field; However, most existing approaches rely on single-modality contexts, such as octree nodes or voxel occupancy, limiting their ability to capture information across large regions. In this paper, we propose PVContext, a hybrid context model for effective octree-based point cloud compression. PVContext comprises two components with distinct modalities: the Voxel Context, which accurately represents local geometric information using voxels, and the Point Context, which efficiently preserves global shape information from point clouds. By integrating these two contexts, we retain detailed information across large areas while controlling the context size. The combined context is then fed into a deep entropy model to accurately predict occupancy. Experimental results demonstrate that, compared to G-PCC, our method reduces the bitrate by 37.95\% on SemanticKITTI LiDAR point clouds and by 48.98\% and 36.36\% on dense object point clouds from MPEG 8i and MVUB, respectively.