Gaussian splatting (GS) struggles with degraded rendering quality on low-cost devices. To address this issue, we present edge collaborative GS (ECO-GS), where each user can switch between a local small GS model to guarantee timeliness and a remote large GS model to guarantee fidelity. However, deciding how to engage the large GS model is nontrivial, due to the interdependency between rendering requirements and resource conditions. To this end, we propose integrated rendering and communication (IRAC), which jointly optimizes collaboration status (i.e., deciding whether to engage large GS) and edge power allocation (i.e., enabling remote rendering) under communication constraints across different users by minimizing a newly-derived GS switching function. Despite the nonconvexity of the problem, we propose an efficient penalty majorization minimization (PMM) algorithm to obtain the critical point solution. Furthermore, we develop an imitation learning optimization (ILO) algorithm, which reduces the computational time by over 100x compared to PMM. Experiments demonstrate the superiority of PMM and the real-time execution capability of ILO.

翻译：高斯泼溅（GS）在低成本设备上存在渲染质量下降的问题。为解决此难题，本文提出边缘协同高斯泼溅（ECO-GS）框架，允许每个用户在保证实时性的本地小型GS模型与保证保真度的远程大型GS模型之间动态切换。然而，由于渲染需求与资源条件之间的相互依赖关系，如何有效调用大型GS模型成为关键挑战。为此，我们提出集成渲染与通信（IRAC）机制，通过最小化新推导的GS切换函数，在通信约束下联合优化多用户间的协同状态（即决定是否调用大型GS）与边缘功率分配（即实现远程渲染）。尽管该问题具有非凸性，我们提出高效的惩罚主化最小化（PMM）算法以获得临界点解。进一步，我们开发了模仿学习优化（ILO）算法，其计算时间较PMM缩短超过100倍。实验验证了PMM的优越性能以及ILO的实时执行能力。