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

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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2025 62nd ACM/IEEE Design Automation Conference (DAC) S. 1 - 7
Hauptverfasser: Li, Sixu, Keller, Ben, Lin, Yingyan Celine, Khailany, Brucek
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 22.06.2025
Schlagworte:
3D Gaussian Splatting
Design automation
Energy consumption
Graphics
Graphics processing units
Graphics Processors
Hardware
Hardware Architecture
Pipelines
Real-time systems
Rendering (computer graphics)
Runtime
Three-dimensional displays
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
DOI:10.1109/DAC63849.2025.11132449