U-Motion: Learned Point Cloud Video Compression with U-Structured Temporal Context Generation
This work addresses compression challenges for point cloud videos, which are important for emerging 3D applications, representing an incremental improvement over existing methods.
The paper tackles the problem of compressing point cloud videos for dynamic scenes by introducing U-Motion, a learning-based scheme that achieves significant gains over MPEG G-PCC-GesTM v3.0 and other learning-based methods in both geometry and attribute compression.
Point cloud video (PCV) is a versatile 3D representation of dynamic scenes with emerging applications. This paper introduces U-Motion, a learning-based compression scheme for both PCV geometry and attributes. We propose a U-Structured inter-frame prediction framework, U-Inter, which performs explicit motion estimation and compensation (ME/MC) at different scales with varying levels of detail. It integrates Top-Down (Fine-to-Coarse) Motion Propagation, Bottom-Up Motion Predictive Coding and Multi-scale Group Motion Compensation to enable accurate motion estimation and efficient motion compression at each scale. In addition, we design a multi-scale spatial-temporal predictive coding module to capture the cross-scale spatial redundancy remaining after U-Inter prediction. We conduct experiments following the MPEG Common Test Condition for dense dynamic point clouds and demonstrate that U-Motion can achieve significant gains over MPEG G-PCC-GesTM v3.0 and recently published learning-based methods for both geometry and attribute compression.