Came across Streamable Gaussian Splatting. You'll never guess the use case though. (Open with Caution)
Summary
A new approach called Streamable Gaussian Splatting enables real-time streaming of 3D scenes, with a potentially surprising application hinted at with caution.
Similar Articles
GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens
GlobalSplat introduces an efficient feed-forward framework for 3D Gaussian splatting that achieves compact and consistent scene reconstruction using global scene tokens, reducing computational overhead and inference time to under 78ms. The method uses a coarse-to-fine training approach to prevent representation bloat while maintaining competitive novel-view synthesis performance with significantly fewer Gaussians (16K) compared to dense baselines.
How to Use Three.js's New Native Gaussian Splats
This article provides a practical guide on using Three.js's native Gaussian Splatting support, explaining how to load and render Gaussian Splats in web 3D scenes with code examples.
Gaussian Point Splatting
Researchers propose Gaussian Point Splatting, a stochastic rendering method using pixel-sized opaque points and 64-bit GPU atomics that scales to hundreds of millions of Gaussians in real time. The method, accepted at SIGGRAPH 2026, employs hierarchical culling and parallel programming primitives to achieve even workload distribution with only minor noise differences compared to original Gaussian splatting.
ZipSplat: Fewer Gaussians, Better Splats
ZipSplat is a token-based feed-forward 3D Gaussian Splatting model that uses k-means clustering to decouple Gaussian placement from the pixel grid, achieving ~6x fewer Gaussians while setting new state-of-the-art results on DL3DV and RealEstate10K without requiring ground-truth poses or intrinsics.
Gaussian Splats part 3: There's always a bigger scene
Magnopus engineer details how their Unreal-based Gaussian splat renderer hit a hidden 16 million splat-per-asset cap via Unreal's GPU Scene, and how bypassing it with a custom DrawIndexedInstancedIndirect pipeline and vertex factory removed the limit entirely.