graphdeco-inria/diff-gaussian-rasterization

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1489 stars · 481 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A CUDA-based differentiable rasterization engine for 3D Gaussian Splatting, used in the SIGGRAPH 2023 paper '3D Gaussian Splatting for Real-Time Rendering of Radiance Fields'. It enables gradient-based optimization of Gaussian primitives for real-time radiance field rendering.

Use cases

• differentiable rasterizer for 3D gaussian splatting training
• render radiance fields in real time
• train novel view synthesis models with gradients through rasterization
• research implementation of gaussian splatting paper
• cuda rasterization engine for graphics research

When to choose

• you are training or extending 3D Gaussian Splatting models
• you need a differentiable rasterization pipeline on CUDA GPUs
• you are doing academic research on radiance fields and novel view synthesis

When to avoid

• you need a general-purpose production renderer
• you have no CUDA-capable GPU
• you need a permissively licensed library for commercial products (license is non-standard)
• you want a ready-to-use application rather than a research component

Facets

library · maturity stable

graphics machine-learning gpu-computing computer-vision graphics deep-learning cpp python gaussian-splatting cuda differentiable-rendering neural-rendering radiance-fields research-code gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="graphdeco-inria/diff-gaussian-rasterization")