让手机实时渲染高质量3D场景，靠边缘协同与智能决策。
Edge Collaborative Gaussian Splatting with Integrated Rendering and Communication
- 用户可切换本地小模型保流畅，远程大模型保画质。
- 联合优化协作状态与通信资源，降低延迟并提升画质。
- 提出高效算法，实现实时推理，适合移动3D应用。
高斯点阵（Gaussian splatting, GS）在低成本设备上渲染质量下降。为此，本文提出边缘协同高斯点阵（ECO-GS），用户可在本地小型模型（保证实时性）与远程大型模型（保证保真度）间切换。然而，在渲染需求与资源条件相互依赖的情况下，决定何时启用大型模型极具挑战。为此，我们提出集成渲染与通信（IRAC），在跨用户通信约束下，联合优化协作状态（是否启用大型模型）与边缘功率分配（支持远程渲染），以最小化新提出的GS切换函数。尽管问题非凸，我们提出高效的惩罚主成分最小化（PMM）算法，获得临界点解；进一步设计模仿学习优化（ILO）算法，计算时间比PMM降低100倍以上。实验验证了PMM的优越性及ILO的实时执行能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。