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

arXiv: https://arxiv.org/abs/2510.13186 · HTML: https://mlsanity.com/paper/2510.13186/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 65 references that are in the map.
- First posted on arXiv 15 Oct 2025.

## Builds on (most cited first, 18 of 18)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [CVXPY: A Python-Embedded Modeling Language for Convex Optimization](https://mlsanity.com/paper/1603.00943/) (2016)
- [Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs](https://mlsanity.com/paper/2112.10703/) (2021)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing](https://mlsanity.com/paper/1905.10083/) (2019)
- [Taming 3DGS: High-Quality Radiance Fields with Limited Resources](https://mlsanity.com/paper/2406.15643/) (2024)
- [FAST-LIO2: Fast Direct LiDAR-inertial Odometry](https://mlsanity.com/paper/2107.06829/) (2021)
- [Adversarial Sampling for Active Learning](https://mlsanity.com/paper/1808.06671/) (2018)
- [DashGaussian: Optimizing 3D Gaussian Splatting in 200 Seconds](https://mlsanity.com/paper/2503.18402/) (2025)
- [Integrated Sensing and Communication with Massive MIMO: A Unified Tensor Approach for Channel and Target Parameter Estimation](https://mlsanity.com/paper/2401.01738/) (2024)
- [Machine Intelligence at the Edge with Learning Centric Power Allocation](https://mlsanity.com/paper/1911.04922/) (2019)
- [A Review on Viewpoints and Path-planning for UAV-based 3D Reconstruction](https://mlsanity.com/paper/2205.03716/) (2022)
- [Fed3DGS: Scalable 3D Gaussian Splatting with Federated Learning](https://mlsanity.com/paper/2403.11460/) (2024)
- [Sparfels: Fast Reconstruction from Sparse Unposed Imagery](https://mlsanity.com/paper/2505.02178/) (2025)
- [Seamless Virtual Reality with Integrated Synchronizer and Synthesizer for Autonomous Driving](https://mlsanity.com/paper/2403.03541/) (2024)
- [Learning Centric Power Allocation for Edge Intelligence](https://mlsanity.com/paper/2007.11399/) (2020)
- [An Efficient Sum-Rate Maximization Algorithm for Fluid Antenna-Assisted ISAC System](https://mlsanity.com/paper/2405.06516/) (2024)
- [MBA-SLAM: Motion Blur Aware Gaussian Splatting SLAM](https://mlsanity.com/paper/2411.08279/) (2024)

## Built on by (most cited first, 2 of 2)

- [LAGS: Low-Altitude Gaussian Splatting with Groupwise Heterogeneous Graph Learning](https://mlsanity.com/paper/2604.16910/) (2026)
- [Efficient Transceiver Design for Aerial Image Transmission and Large-scale Scene Reconstruction](https://mlsanity.com/paper/2604.11098/) (2026)

## Abstract (arXiv)

Edge Gaussian splatting (EGS), which aggregates data from distributed clients (e.g., drones) and trains a global GS model at the edge (e.g., ground server), is an emerging paradigm for scene reconstruction in low-altitude economy. 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 reveal that the proposed scheme significantly outperforms existing benchmarks on real-world datasets. 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.