Learning Dynamic Point Cloud Compression via Hierarchical Inter-frame Block Matching
This work addresses compression challenges for dynamic point clouds, which are crucial for applications like virtual reality and autonomous driving, representing an incremental improvement over existing methods.
The paper tackles the problem of compressing 3D dynamic point clouds by proposing a learning-based framework with hierarchical inter-prediction and KNN-attention block matching, achieving state-of-the-art performance on the Owlii dataset compared to previous methods and the MPEG V-PCC v18 standard.
3D dynamic point cloud (DPC) compression relies on mining its temporal context, which faces significant challenges due to DPC's sparsity and non-uniform structure. Existing methods are limited in capturing sufficient temporal dependencies. Therefore, this paper proposes a learning-based DPC compression framework via hierarchical block-matching-based inter-prediction module to compensate and compress the DPC geometry in latent space. Specifically, we propose a hierarchical motion estimation and motion compensation (Hie-ME/MC) framework for flexible inter-prediction, which dynamically selects the granularity of optical flow to encapsulate the motion information accurately. To improve the motion estimation efficiency of the proposed inter-prediction module, we further design a KNN-attention block matching (KABM) network that determines the impact of potential corresponding points based on the geometry and feature correlation. Finally, we compress the residual and the multi-scale optical flow with a fully-factorized deep entropy model. The experiment result on the MPEG-specified Owlii Dynamic Human Dynamic Point Cloud (Owlii) dataset shows that our framework outperforms the previous state-of-the-art methods and the MPEG standard V-PCC v18 in inter-frame low-delay mode.