AI & ML Efficiency Breakthrough

The first sorting-free stochastic formulation for 3D Gaussian Splatting that matches rasterization speed while enabling full ray-traced effects.

March 26, 2026

Original Paper

Stochastic Ray Tracing for the Reconstruction of 3D Gaussian Splatting

Peiyu Xu, Xin Sun, Krishna Mullia, Raymond Fei, Iliyan Georgiev, Shuang Zhao

arXiv · 2603.23637

The Takeaway

Sorting Gaussians along a ray is the primary bottleneck for ray-traced 3DGS. This paper introduces an unbiased Monte Carlo estimator that bypasses sorting entirely, allowing for high-fidelity 3D reconstruction and relighting with significantly lower computational overhead.

From the abstract

Ray-tracing-based 3D Gaussian splatting (3DGS) methods overcome the limitations of rasterization -- rigid pinhole camera assumptions, inaccurate shadows, and lack of native reflection or refraction -- but remain slower due to the cost of sorting all intersecting Gaussians along every ray. Moreover, existing ray-tracing methods still rely on rasterization-style approximations such as shadow mapping for relightable scenes, undermining the generality that ray tracing promises.We present a different