Point cloud streaming is increasingly getting popular, evolving into the norm for interactive service delivery and the future Metaverse. However, the substantial volume of data associated with point clouds presents numerous challenges, particularly in terms of high bandwidth consumption and large storage capacity. Despite various solutions proposed thus far, with a focus on point cloud compression, upsampling, and completion, these reconstruction-related methods continue to fall short in delivering high fidelity point cloud output. As a solution, in DiffPMAE, we propose an effective point cloud reconstruction architecture. Inspired by self-supervised learning concepts, we combine Masked Auto-Encoding and Diffusion Model mechanism to remotely reconstruct point cloud data. By the nature of this reconstruction process, DiffPMAE can be extended to many related downstream tasks including point cloud compression, upsampling and completion. Leveraging ShapeNet-55 and ModelNet datasets with over 60000 objects, we validate the performance of DiffPMAE exceeding many state-of-the-art methods in-terms of auto-encoding and downstream tasks considered.

翻译：点云流媒体正日益普及，逐渐成为交互式服务交付和未来元宇宙的标准。然而，与点云相关的大量数据带来了诸多挑战，尤其是在高带宽消耗和大存储容量方面。尽管目前已提出多种解决方案，聚焦于点云压缩、上采样和补全，但这些与重建相关的方法在生成高保真点云输出方面仍存在不足。为解决这一问题，我们在DiffPMAE中提出了一种高效的点云重建架构。受自监督学习概念的启发，我们将掩码自编码与扩散模型机制相结合，以实现远程点云数据重建。基于这一重建过程的特性，DiffPMAE可扩展至许多相关下游任务，包括点云压缩、上采样和补全。利用包含超过60000个物体的ShapeNet-55和ModelNet数据集，我们验证了DiffPMAE在自编码及相关下游任务上的性能超越了多种当前最优方法。