Edge Collaborative Gaussian Splatting with Integrated Rendering and Communication

2025-10-26

AI Summary

To address the significant degradation in rendering quality of Gaussian Splatting (GS) on resource-constrained edge devices, this paper proposes an edge–cloud collaborative rendering framework. Methodologically, it introduces (1) an Integrated Rendering-and-Communication (IRAC) optimization mechanism; (2) a GS rendering mode adaptation strategy based on a dynamic switching function; and (3) a Penalty-based Majorization-Minimization (PMM) algorithm to solve the non-convex collaborative optimization problem, accelerated by an Imitation Learning-based Optimization (ILO) method achieving over 100× speedup. Experimental results demonstrate that, under strict end-to-end latency constraints, the framework improves rendering PSNR by 3.2 dB, ensures real-time ILO execution, and reduces system resource overhead by 67%.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

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.

Problem

• Optimizing rendering quality for low-cost devices
• Balancing local and remote Gaussian splatting models
• Jointly managing rendering and communication resource allocation

Innovation

• Edge collaboration switches between local and remote models
• Integrated rendering and communication optimizes resource allocation
• Imitation learning reduces computation time by over 100x