# EvoGS: Constructing Continuous-Layered Gaussian Splatting with Evolution Tree for Scalable 3D Streaming

arXiv: https://arxiv.org/abs/2606.07179 · HTML: https://mlsanity.com/paper/2606.07179/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 5 Jun 2026.

## Builds on (most cited first, 9 of 9)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering](https://mlsanity.com/paper/2312.00109/) (2023)
- [A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets](https://mlsanity.com/paper/2406.12080/) (2024)
- [CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians](https://mlsanity.com/paper/2404.01133/) (2024)
- [Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering](https://mlsanity.com/paper/2311.17089/) (2023)
- [Sketch and Patch: Efficient 3D Gaussian Representation for Man-Made Scenes](https://mlsanity.com/paper/2501.13045/) (2025)
- [Volumetric video streaming: Current approaches and implementations](https://mlsanity.com/paper/2209.01982/) (2022)
- [L3GS: Layered 3D Gaussian Splats for Efficient 3D Scene Delivery](https://mlsanity.com/paper/2504.05517/) (2025)
- [Adaptive 3D Gaussian Splatting Video Streaming](https://mlsanity.com/paper/2507.14432/) (2025)

## Abstract (arXiv)

Streaming 3D Gaussian Splatting requires highly scalable, progressive representations. Existing progressive methods rely on textitdiscrete layering, accumulating separate splat sets for each level of detail. This structural independence between layers inherently leads to error accumulation, severe splat redundancy, and uncontrolled quality transitions. We propose EvoGS, the first textitcontinuous-layering representation. Organized as an Evolution Tree, EvoGS generates finer details via an explicit, wavelet-inspired parent-child refinement. This empowers child nodes to structurally correct ancestral errors, yield inherently sparse and highly compressible inter-layer signals. Extensive experiments show EvoGS eliminates splat redundancy from over 65% to under 25%. Compared to state-of-the-art baselines, it reduces transmission payload and GPU VRAM footprint by up to 2.4× and 5.5×, respectively, and achieves smooth quality transitions optimal for real-time adaptive streaming. Project page: https://yuang-ian.github.io/evogs/