# hbb1/2d-gaussian-splatting

[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

Repository: https://github.com/hbb1/2d-gaussian-splatting
Canonical: https://ross.abutalabs.com/products/2d-gaussian-splatting
Homepage: https://surfsplatting.github.io
Language: Python
License: NOASSERTION
License Family: other
Topics: novel-view-synthesis, surface-reconstruction, gaussian-splatting
Last push: 2026-08-25T18:36:57+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 61
- inputs: {"age_days": 858, "days_push": 8, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3279, forks 324 (observed 2026-08-28T04:07:53.525296+00:00)

## What it is
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
- artifact type: library
- maturity: stable
- function: graphics, machine-learning, image-processing, simulation
- domain: computer-vision, graphics, machine-learning, deep-learning
- platform: python, cross-platform
- tags: gaussian-splatting, novel-view-synthesis, surface-reconstruction, radiance-fields, differentiable-rendering, mesh-extraction, cuda, research-code, siggraph, linux, gpu

## Member repositories
- hbb1/2d-gaussian-splatting (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:53.525296+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:43:20.818759+00:00, confidence not recorded.
  - readme: https://github.com/hbb1/2d-gaussian-splatting (fetched 2026-08-28T04:07:53.525296+00:00, sha 26f2606369c1)
  - homepage: https://surfsplatting.github.io (fetched 2026-08-29T09:36:10.649675+00:00, sha 0cc7b1d84305)
- Data as of 2026-08-30T08:39:29.467469+00:00.