# Federated 3D Gaussian Splatting for Large-Scale Scene Reconstruction at Wireless Edge

arXiv: https://arxiv.org/abs/2609.32177 · HTML: https://mlsanity.com/paper/2609.32177/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 46 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Builds on (most cited first, 30 of 30)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [Flower: A Friendly Federated Learning Research Framework](https://mlsanity.com/paper/2007.14390/) (2020)
- [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://mlsanity.com/paper/2311.17245/) (2023)
- [Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs](https://mlsanity.com/paper/2112.10703/) (2021)
- [DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes](https://mlsanity.com/paper/2312.07920/) (2023)
- [A Survey on 3D Gaussian Splatting](https://mlsanity.com/paper/2401.03890/) (2024)
- [Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians](https://mlsanity.com/paper/2403.14166/) (2024)
- [VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction](https://mlsanity.com/paper/2402.17427/) (2024)
- [EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS](https://mlsanity.com/paper/2312.04564/) (2023)
- [CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians](https://mlsanity.com/paper/2404.01133/) (2024)
- [Capturing, Reconstructing, and Simulating: the UrbanScene3D Dataset](https://mlsanity.com/paper/2107.04286/) (2021)
- [Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications](https://mlsanity.com/paper/2111.12444/) (2021)
- [3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities](https://mlsanity.com/paper/2407.17418/) (2024)
- [Splat-Nav: Safe Real-Time Robot Navigation in Gaussian Splatting Maps](https://mlsanity.com/paper/2403.02751/) (2024)
- [DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus](https://mlsanity.com/paper/2405.13943/) (2024)
- [On Scaling Up 3D Gaussian Splatting Training](https://mlsanity.com/paper/2406.18533/) (2024)
- [PatrickStar: Parallel Training of Pre-trained Models via Chunk-based Memory Management](https://mlsanity.com/paper/2108.05818/) (2021)
- [Forecasting GPU Performance for Deep Learning Training and Inference](https://mlsanity.com/paper/2407.13853/) (2024)
- [NeRF Is a Valuable Assistant for 3D Gaussian Splatting](https://mlsanity.com/paper/2507.23374/) (2025)
- [Omni-swarm: A Decentralized Omnidirectional Visual-Inertial-UWB State Estimation System for Aerial Swarms](https://mlsanity.com/paper/2103.04131/) (2021)
- [Fed3DGS: Scalable 3D Gaussian Splatting with Federated Learning](https://mlsanity.com/paper/2403.11460/) (2024)
- [LLMem: Estimating GPU Memory Usage for Fine-Tuning Pre-Trained LLMs](https://mlsanity.com/paper/2404.10933/) (2024)
- [CoSurfGS:Collaborative 3D Surface Gaussian Splatting with Distributed Learning for Large Scene Reconstruction](https://mlsanity.com/paper/2412.17612/) (2024)
- [Federated Learning for Large-Scale Scene Modeling with Neural Radiance Fields](https://mlsanity.com/paper/2309.06030/) (2023)
- [DGTR: Distributed Gaussian Turbo-Reconstruction for Sparse-View Vast Scenes](https://mlsanity.com/paper/2411.12309/) (2024)
- [A Comparison Study of Cellular Deployments in Chicago and Miami Using Apps on Smartphones](https://mlsanity.com/paper/2108.00453/) (2021)
- [Radiant: Large-scale 3D Gaussian Rendering based on Hierarchical Framework](https://mlsanity.com/paper/2412.05546/) (2024)

## Abstract (arXiv)

Three-dimensional (3D) Gaussian splatting (3D-GS) has emerged as a promising technique for large-scale scene reconstruction due to its high rendering efficiency and fidelity. However, the training of large-scale 3D-GS models at wireless edge faces various technical challenges including the limited communication, computation, and graphics processing unit (GPU) memory resources at edge devices, the structural inconsistency issue across local models hindering their effective aggregation, as well as privacy leakage risks associated with raw visual content and camera parameters. To address these challenges, this paper proposes a novel resource-efficient federated learning framework for efficiently training 3D-GS models of large scenes under severe resource constraints. First, we propose an on-device model lightweighting mechanism that adaptively selects and prunes Gaussian points to balance the rendering quality and training efficiency. In this mechanism, we quantitatively evaluate the importance of different Gaussian points at each device to facilitate the pruning, and use a novel importance-to-latency ratio criterion to determine the number of pruned Gaussian points under GPU memory and computation/communication latency constraints. Furthermore, we develop a 3D-GS model recovery mechanism that restores structural consistency across local 3D-GS models without accessing private camera parameters, enabling their effective aggregation towards a global model. Finally, extensive experiments show that our approach significantly accelerates convergence, maintains high rendering quality, and reduces training latency compared to state-of-the-art federated 3D-GS baselines.