Skip to main content

> ML_ARCHITECTURE // 3D-GAUSSIAN-SPLATTING-RENDERER_v1.0

3D Gaussian Splatting (Rasterized Scene Representation)

Explicit 3D radiance field representation modeling scenes as anisotropic 3D Gaussian primitives rasterized using GPU tile sorting, delivering photorealistic real-time interactive 100+ FPS rendering.

3D Neural Representations3d-pointcloudsimage
Back to All Architectures

Architecture Overview

Explicit 3D radiance field representation modeling scenes as anisotropic 3D Gaussian primitives rasterized using GPU tile sorting, delivering photorealistic real-time interactive 100+ FPS rendering.

Implementing Libraries

PyTorchLinux Foundation / PyTorch Foundation · v2.4.1
View Spec

Seminal Papers

3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas (2023) · ACM Transactions on Graphics (SIGGRAPH)
Architectural Limitations & Constraints
  • Requires compatible deep learning framework and hardware acceleration for efficient execution.