# MoE-GS: Mixture of Experts for Dynamic Gaussian Splatting

arXiv: https://arxiv.org/abs/2510.19210 · HTML: https://mlsanity.com/paper/2510.19210/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts.
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Placed in

- Mixture-of-experts / [Vision mixture-of-experts](https://mlsanity.com/moe/vision-mixture-of-experts/)

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

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [K-Planes: Explicit Radiance Fields in Space, Time, and Appearance](https://mlsanity.com/paper/2301.10241/) (2023)
- [Dynamic View Synthesis from Dynamic Monocular Video](https://mlsanity.com/paper/2105.06468/) (2021)
- [Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis](https://mlsanity.com/paper/2312.16812/) (2023)
- [HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling](https://mlsanity.com/paper/2301.02238/) (2023)
- [3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos](https://mlsanity.com/paper/2403.01444/) (2024)
- [Mixed Neural Voxels for Fast Multi-view Video Synthesis](https://mlsanity.com/paper/2212.00190/) (2022)
- [Per-Gaussian Embedding-Based Deformation for Deformable 3D Gaussian Splatting](https://mlsanity.com/paper/2404.03613/) (2024)
- [Fully Explicit Dynamic Gaussian Splatting](https://mlsanity.com/paper/2410.15629/) (2024)
- [4D Gaussian Splatting with Scale-aware Residual Field and Adaptive Optimization for Real-time Rendering of Temporally Complex Dynamic Scenes](https://mlsanity.com/paper/2412.06299/) (2024)
- [MoDE: A Mixture-of-Experts Model with Mutual Distillation among the Experts](https://mlsanity.com/paper/2402.00893/) (2024)
- [SwinGS: Sliding Window Gaussian Splatting for Volumetric Video Streaming with Arbitrary Length](https://mlsanity.com/paper/2409.07759/) (2024)

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

- [TRiGS: Temporal Rigid-Body Motion for Scalable 4D Gaussian Splatting](https://mlsanity.com/paper/2604.00538/) (2026)
- [On the Design of Mixture-of-Experts for Dynamic Gaussian Splatting](https://mlsanity.com/paper/2607.08250/) (2026)

## Abstract (arXiv)

Recent advances in dynamic scene reconstruction have significantly benefited from 3D Gaussian Splatting, yet existing methods show inconsistent performance across diverse scenes, indicating no single approach effectively handles all dynamic challenges. To overcome these limitations, we propose Mixture of Experts for Dynamic Gaussian Splatting (MoE-GS), a unified framework integrating multiple specialized experts via a novel Volume-aware Pixel Router. Unlike sparsity-oriented MoE architectures in large language models, MoE-GS is designed to improve dynamic novel view synthesis quality by combining heterogeneous deformation priors, rather than to reduce training or inference-time FLOPs. Our router adaptively blends expert outputs by projecting volumetric Gaussian-level weights into pixel space through differentiable weight splatting, ensuring spatially and temporally coherent results. Although MoE-GS improves rendering quality, the increased model capacity and reduced FPS are inherent to the MoE architecture. To mitigate this, we explore two complementary directions: (1) single-pass multi-expert rendering and gate-aware Gaussian pruning, which improve efficiency within the MoE framework, and (2) a distillation strategy that transfers MoE performance to individual experts, enabling lightweight deployment without architectural changes. To the best of our knowledge, MoE-GS is the first approach incorporating Mixture-of-Experts techniques into dynamic Gaussian splatting. Extensive experiments on the N3V and Technicolor datasets demonstrate that MoE-GS consistently outperforms state-of-the-art methods with improved efficiency. Video demonstrations are available at cvsp-lab.github.io/MoE-GS.