AI & ML New Capability

Introduces the first inherently scalable primitive for radiance fields, allowing real-time Level-of-Detail (LOD) rendering by simply truncating Fourier coefficients.

March 23, 2026

Original Paper

Fourier Splatting: Generalized Fourier encoded primitives for scalable radiance fields

Mihnea-Bogdan Jurca, Bert Van hauwermeiren, Adrian Munteanu

arXiv · 2603.19834

The Takeaway

Currently, 3D Gaussian Splatting quality is tied to the number of primitives, making downscaling difficult. This method allows a single trained model to scale its rendering fidelity and bandwidth consumption at runtime, essential for deploying high-fidelity 3D scenes on diverse hardware.

From the abstract

Novel view synthesis has recently been revolutionized by 3D Gaussian Splatting (3DGS), which enables real-time rendering through explicit primitive rasterization. However, existing methods tie visual fidelity strictly to the number of primitives: quality downscaling is achieved only through pruning primitives. We propose the first inherently scalable primitive for radiance field rendering. Fourier Splatting employs scalable primitives with arbitrary closed shapes obtained by parameterizing plana