CERender: Real-Time Cloud Rendering Based on Cloud-Edge Collaboration

With the maturity of cloud computing and the rise of edge computing, real-time cloud rendering technology has received widespread attention for its ability to solve the problem of low-power mobile devices. Cloud rendering still faces challenges in providing users with stable, high-quality and real-time interactive experiences due to the limitations of the network environment and the cost of computing resources. A cloud-edge collaborative rendering model is proposed in this paper, in order to reduce the computing resource burden on the edge side by using cloud-side computing power and reusing rendering computation results. At the same time, a set of dynamic update strategies is designed to address the high downstream bandwidth burden brought by the model. Finally, experiments show that the introduction of edge computing can significantly reduce network latency and interaction latency compared to cloud-centric solutions. At the same time, by introducing the NetGI component of cloud-edge co-rendering, the frame rate is increased by more than 20% in the scene of large multi-dynamic lighting sources compared with the pure edge-end rendering solution.