STT-GS: Sample-Then-Transmit Edge Gaussian Splatting with Joint Client Selection and Power Control

2025-10-15

AI Summary

Existing resource management methods for edge Gaussian Splatting (EGS) scene reconstruction struggle to jointly optimize Gaussian Splatting (GS) reconstruction quality and communication efficiency. Method: This paper proposes the Sample-Then-Transmit Gaussian Splatting (STT-GS) framework. It introduces, for the first time, an end-to-end optimization objective explicitly designed for GS quality; develops a pilot-data-driven view contribution pre-evaluation mechanism to overcome causal constraints; and jointly optimizes client selection and power control via three novel algorithms—Feature-domain Clustering (FDC), Pilot Transmission Time Minimization (PTTM), and Penalty-based Alternating Majorization-Minimization (PAMM). Contribution/Results: Experiments demonstrate that STT-GS achieves highly accurate view contribution prediction at only 10% sampling rate, significantly improving reconstruction quality while reducing communication overhead—outperforming state-of-the-art edge learning and reconstruction approaches.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Security and Privacy: Data transparency and provenance

Abstract

Edge Gaussian splatting (EGS), which aggregates data from distributed clients and trains a global GS model at the edge server, is an emerging paradigm for scene reconstruction. Unlike traditional edge resource management methods that emphasize communication throughput or general-purpose learning performance, EGS explicitly aims to maximize the GS qualities, rendering existing approaches inapplicable. To address this problem, this paper formulates a novel GS-oriented objective function that distinguishes the heterogeneous view contributions of different clients. However, evaluating this function in turn requires clients' images, leading to a causality dilemma. To this end, this paper further proposes a sample-then-transmit EGS (or STT-GS for short) strategy, which first samples a subset of images as pilot data from each client for loss prediction. Based on the first-stage evaluation, communication resources are then prioritized towards more valuable clients. To achieve efficient sampling, a feature-domain clustering (FDC) scheme is proposed to select the most representative data and pilot transmission time minimization (PTTM) is adopted to reduce the pilot overhead.Subsequently, we develop a joint client selection and power control (JCSPC) framework to maximize the GS-oriented function under communication resource constraints. Despite the nonconvexity of the problem, we propose a low-complexity efficient solution based on the penalty alternating majorization minimization (PAMM) algorithm. Experiments unveil that the proposed scheme significantly outperforms existing benchmarks on real-world datasets. It is found that the GS-oriented objective can be accurately predicted with low sampling ratios (e.g.,10%), and our method achieves an excellent tradeoff between view contributions and communication costs.

Problem

• Maximizes Gaussian splatting quality through client selection and power control
• Solves causality dilemma in evaluating view contributions with pilot sampling
• Optimizes communication resource allocation under nonconvex constraints efficiently

Innovation

• Sample-then-transmit strategy with pilot data collection
• Feature-domain clustering for representative data selection
• Joint client selection and power control optimization