hbb1/2d-gaussian-splatting

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

3279 stars · 324 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Official implementation of 2D Gaussian Splatting (2DGS), a SIGGRAPH 2024 method that represents scenes as 2D oriented Gaussian disks for geometrically accurate radiance field reconstruction from multi-view images. It provides differentiable surfel rasterization, depth distortion and normal consistency regularization, and mesh extraction including unbounded scenes.

Use cases

• reconstruct accurate 3D surfaces from multi-view photos
• novel view synthesis with view-consistent geometry
• extract textured meshes from gaussian splatting scenes
• reconstruct unbounded scenes with mesh extraction
• compare 3DGS vs 2DGS geometry quality
• train radiance fields with fast real-time rendering

When to choose

• you need accurate surface geometry or meshes, not just photorealistic rendering
• you want a research-grade, well-cited gaussian splatting implementation with CUDA rasterizer
• you need unbounded scene meshing with adaptive TSDF truncation

When to avoid

• you only need simple photorealistic rendering without geometry accuracy
• you lack a CUDA-capable GPU
• you need a production-ready application with a polished UI rather than research code

Facets

library · maturity stable

graphics machine-learning image-processing simulation computer-vision graphics machine-learning deep-learning python cross-platform gaussian-splatting novel-view-synthesis surface-reconstruction radiance-fields differentiable-rendering mesh-extraction cuda research-code siggraph linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="hbb1/2d-gaussian-splatting")