Mesla: Neural Adaptive Layered Point Cloud Streaming with Enhanced Buffer Management

Point cloud video provides an immersive experience with six degrees of freedom (6DoF). However, streaming video imposes significant challenges due to the huge data volume involved, which increases the transmission burden and makes it difficult to maintain a high quality of experience (QoE) in bandwidth-constrained networks. Current methods either employ pre-specified control rules or make irreversible decisions to optimize the QoE, hindering adaptation to the varying network conditions and not employing buffer management. In this work, we present Mesla ¹, an adaptive layered point cloud streaming framework, which is empowered by deep reinforcement learning (DRL) and hierarchical buffer management. By maximizing the utility-driven QoE via proximal policy optimization (PPO)-based DRL, Mesla makes bitrate decisions based on the obtained network observations and viewing behaviors of users. The viewport-oriented utility is incorporated into the QoE objective for assigning point cloud tiles with different priorities. To achieve fine-grained rate adaptation, we partition point clouds into layers with different levels of details (LoD) and develop a buffering heuristic (i.e., the hierarchical buffer management) that enhances the quality of unconsumed content. Extensive simulations demonstrate the advantages of Mesla compared to the benchmarking schemes, corroborating the effectiveness of the proposed system.