Universal Beta Splatting

Rong Liu1,2 Zhongpai Gao2* Benjamin Planche2 Meida Chen1
Van Nguyen Nguyen2 Meng Zheng2 Anwesa Choudhuri2
Terrence Chen2 Yue Wang1 Andrew Feng1 Ziyan Wu2

*Corresponding author

1University of Southern California
2United Imaging Intelligence
Teaser

UBS achieves superior angular-spatial rendering of reflective and specular materials in static scenes (left) and maintains high-fidelity temporal-spatial reconstruction in dynamic volumetric scenes (right), avoiding the blurring artifacts of 3DGS and 4DGS.

Abstract

We introduce Universal Beta Splatting (UBS), a unified framework that generalizes 3D Gaussian Splatting to N-dimensional anisotropic Beta kernels for explicit radiance field rendering. Unlike fixed Gaussian primitives, Beta kernels enable controllable dependency modeling across spatial, angular, and temporal dimensions within a single representation. Our unified approach captures complex light transport effects, handles anisotropic view-dependent appearance, and models scene dynamics without requiring auxiliary networks or specific color encodings. UBS maintains backward compatibility by approximating to Gaussian Splatting as a special case, guaranteeing plug-in usability and lower performance bounds. The learned Beta parameters naturally decompose scene properties without explicit supervision: spatial (surface vs. texture), angular (diffuse vs. specular), and temporal (static vs. dynamic). Our CUDA-accelerated implementation achieves real-time rendering while consistently outperforming existing methods across static, view-dependent, and dynamic benchmarks, establishing Beta kernels as a scalable universal primitive for radiance field rendering.

Demo Video

Static Reconstruction

GT 3DGS 6DGS Ours

Dynamic Reconstruction

GT 4DGS 7DGS Ours

Related Links

[1] 3D Gaussian Splatting for Real-Time Radiance Field Rendering in SIGGRAPH 2023
[2] Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting in ICLR 2024
[3] 6DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric Rendering in ICLR 2025
[4] 7DGS: Unified Spatial-Temporal-Angular Gaussian Splatting in ICCV 2025
[5] Deformable Beta Splatting in SIGGRAPH 2025

BibTeX

@misc{liu2025universalbetasplatting,
    title={Universal Beta Splatting}, 
    author={Rong Liu and Zhongpai Gao and Benjamin Planche and Meida Chen and Van Nguyen Nguyen and Meng Zheng and Anwesa Choudhuri and Terrence Chen and Yue Wang and Andrew Feng and Ziyan Wu},
    year={2025},
    eprint={2510.03312},
    archivePrefix={arXiv},
    primaryClass={cs.GR},
    url={https://arxiv.org/abs/2510.03312}, 
}