# GauRast: Enhancing GPU Triangle Rasterizers to Accelerate 3D Gaussian Splatting

arXiv: https://arxiv.org/abs/2503.16681 · HTML: https://mlsanity.com/paper/2503.16681/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 38 references that are in the map.
- First posted on arXiv 20 Mar 2025.

## Builds on (most cited first, 15 of 15)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Gaussian Splatting SLAM](https://mlsanity.com/paper/2312.06741/) (2023)
- [DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes](https://mlsanity.com/paper/2312.07920/) (2023)
- [Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians](https://mlsanity.com/paper/2403.14166/) (2024)
- [3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting](https://mlsanity.com/paper/2312.09228/) (2023)
- [Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation](https://mlsanity.com/paper/2308.07931/) (2023)
- [S-NeRF: Neural Radiance Fields for Street Views](https://mlsanity.com/paper/2303.00749/) (2023)
- [textitS3Gaussian: Self-Supervised Street Gaussians for Autonomous Driving](https://mlsanity.com/paper/2405.20323/) (2024)
- [GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning](https://mlsanity.com/paper/2312.11461/) (2023)
- [CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Field](https://mlsanity.com/paper/2403.16095/) (2024)
- [3D Gaussian Blendshapes for Head Avatar Animation](https://mlsanity.com/paper/2404.19398/) (2024)
- [Instant-3D: Instant Neural Radiance Field Training Towards On-Device AR/VR 3D Reconstruction](https://mlsanity.com/paper/2304.12467/) (2023)
- [Cicero: Addressing Algorithmic and Architectural Bottlenecks in Neural Rendering by Radiance Warping and Memory Optimizations](https://mlsanity.com/paper/2404.11852/) (2024)
- [GSPR: Multimodal Place Recognition Using 3D Gaussian Splatting for Autonomous Driving](https://mlsanity.com/paper/2410.00299/) (2024)

## Built on by (most cited first, 6 of 6)

- [Faster-GS: Analyzing and Improving Gaussian Splatting Optimization](https://mlsanity.com/paper/2602.09999/) (2026)
- [Efficient 3D Gaussian Splatting with Axis-Shared Rasterization and Order-independent Transmittance](https://mlsanity.com/paper/2506.07069/) (2025)
- [HiGS: A Hierarchical Rendering Architecture for Real-Time 3D Gaussian Splatting](https://mlsanity.com/paper/2606.00352/) (2026)
- [DeGS: A Scalable 3DGS Architecture via Decoupled Workload Parsing and Reorganization](https://mlsanity.com/paper/2608.02099/) (2026)
- [CaT-GS: Efficient 3DGS Rendering for Large Scale Scenes via Inter-frame Caching and Tile Scheduling](https://mlsanity.com/paper/2607.17842/) (2026)
- [From Splats to Silicon: Rethinking Computational Efficiency of 3DGS](https://mlsanity.com/paper/2609.06157/) (2026)

## Abstract (arXiv)

3D intelligence leverages rich 3D features and stands as a promising frontier in AI, with 3D rendering fundamental to many downstream applications. 3D Gaussian Splatting (3DGS), an emerging high-quality 3D rendering method, requires significant computation, making real-time execution on existing GPU-equipped edge devices infeasible. Previous efforts to accelerate 3DGS rely on dedicated accelerators that require substantial integration overhead and hardware costs. This work proposes an acceleration strategy that leverages the similarities between the 3DGS pipeline and the highly optimized conventional graphics pipeline in modern GPUs. Instead of developing a dedicated accelerator, we enhance existing GPU rasterizer hardware to efficiently support 3DGS operations. Our results demonstrate a 23× increase in processing speed and a 24× reduction in energy consumption, with improvements yielding 6× faster end-to-end runtime for the original 3DGS algorithm and 4× for the latest efficiency-improved pipeline, achieving 24 FPS and 46 FPS respectively. These enhancements incur only a minimal area overhead of 0.2% relative to the entire SoC chip area, underscoring the practicality and efficiency of our approach for enabling 3DGS rendering on resource-constrained platforms.