# STREAMINGGS: Voxel-Based Streaming 3D Gaussian Splatting with Memory Optimization and Architectural Support

arXiv: https://arxiv.org/abs/2506.09070 · HTML: https://mlsanity.com/paper/2506.09070/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 28 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Builds on (most cited first, 13 of 13)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://mlsanity.com/paper/2311.17245/) (2023)
- [Compact 3D Gaussian Representation for Radiance Field](https://mlsanity.com/paper/2311.13681/) (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)
- [Recent Advances in 3D Gaussian Splatting](https://mlsanity.com/paper/2403.11134/) (2024)
- [DeepScaleTool : A Tool for the Accurate Estimation of Technology Scaling in the Deep-Submicron Era](https://mlsanity.com/paper/2102.10195/) (2021)
- [MetaSapiens: Real-Time Neural Rendering with Efficiency-Aware Pruning and Accelerated Foveated Rendering](https://mlsanity.com/paper/2407.00435/) (2024)
- [Cicero: Addressing Algorithmic and Architectural Bottlenecks in Neural Rendering by Radiance Warping and Memory Optimizations](https://mlsanity.com/paper/2404.11852/) (2024)
- [SeeLe: A Unified Acceleration Framework for Real-Time Gaussian Splatting](https://mlsanity.com/paper/2503.05168/) (2025)
- [Potamoi: Accelerating Neural Rendering via a Unified Streaming Architecture](https://mlsanity.com/paper/2408.06608/) (2024)

## Built on by (most cited first, 3 of 3)

- [Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication](https://mlsanity.com/paper/2606.18588/) (2026)
- [RoofGS: Roofline-Guided End-to-End Acceleration of 3D Gaussian Splatting](https://mlsanity.com/paper/2608.15785/) (2026)
- [From Splats to Silicon: Rethinking Computational Efficiency of 3DGS](https://mlsanity.com/paper/2609.06157/) (2026)

## Abstract (arXiv)

3D Gaussian Splatting (3DGS) has gained popularity for its efficiency and sparse Gaussian-based representation. However, 3DGS struggles to meet the real-time requirement of 90 frames per second (FPS) on resource-constrained mobile devices, achieving only 2 to 9 FPS.Existing accelerators focus on compute efficiency but overlook memory efficiency, leading to redundant DRAM traffic. We introduce STREAMINGGS, a fully streaming 3DGS algorithm-architecture co-design that achieves fine-grained pipelining and reduces DRAM traffic by transforming from a tile-centric rendering to a memory-centric rendering. Results show that our design achieves up to 45.7 × speedup and 62.9 × energy savings over mobile Ampere GPUs.