yzslab/gaussian-splatting-lightning

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

1107 stars · 85 forks observed · 2026-10-04

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

A PyTorch Lightning implementation of 3D Gaussian Splatting with many derived algorithms (Mip-Splatting, LightGaussian, 2DGS, deformable Gaussians, etc.) and an interactive web viewer. It supports multi-GPU training, multiple dataset formats, and video rendering.

Use cases

• train 3d gaussian splatting models from colmap captures
• reconstruct 3d scenes from photos with multi-gpu training
• view and edit gaussian splatting models in a browser
• render camera path videos from trained splat models
• try research variants like mip-splatting or 2dgs
• segment or deform gaussian splat scenes

When to choose

• you want a maintained, feature-rich 3DGS training framework with many derived algorithms
• you need multi-GPU/node training or large image datasets without OOM
• you want an interactive web viewer and scene editor for splat models

When to avoid

• you need a simple one-command pipeline with minimal configuration
• you require a permissive license (license is non-standard)
• you work outside Python/PyTorch ecosystems

Facets

library · maturity active

machine-learning deep-learning graphics simulation data-visualization computer-vision graphics machine-learning deep-learning python cross-platform gaussian-splatting pytorch-lightning neural-rendering 3d-reconstruction nerf web-viewer multi-gpu gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="yzslab/gaussian-splatting-lightning")