# Anttwo/SuGaR

[CVPR 2024] Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

Repository: https://github.com/Anttwo/SuGaR
Canonical: https://ross.abutalabs.com/products/anttwo-sugar
Homepage: https://anttwo.github.io/sugar/
Language: C++
License: NOASSERTION
License Family: other
Topics: 3d-gaussian-splatting, 3dgs, gaussian-splatting, mesh, mesh-generation, nerf, neural-rendering, surface-reconstruction, cvpr2024
Last push: 2024-09-24T15:13:31+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 72
- inputs: {"age_days": 1010, "days_push": 708, "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 3495, forks 306 (observed 2026-08-28T04:08:07.309605+00:00)

## What it is
SuGaR is the official PyTorch implementation of a CVPR 2024 method that extracts accurate, editable meshes from 3D Gaussian Splatting reconstructions within minutes on a single GPU. It binds Gaussians to mesh surfaces, enabling editing, animation, and relighting in tools like Blender, Unity, and Unreal while preserving high-quality Gaussian Splatting rendering.

## Use cases
- extract a mesh from 3D gaussian splatting scenes
- reconstruct editable 3D surfaces from photos
- animate gaussian splatting scenes in blender
- convert 3DGS reconstructions to textured meshes
- edit and rig gaussian splatting scenes via a mesh
- fast mesh extraction from neural radiance representations

## When to choose
- you need editable meshes from 3D Gaussian Splatting reconstructions quickly
- you want to animate or composite Gaussian Splatting scenes in Blender, Unity, or Unreal
- you need faster mesh extraction than neural SDF methods with better rendering quality

## When to avoid
- you only need novel-view rendering without meshes, where vanilla 3D Gaussian Splatting suffices
- you lack a CUDA-capable GPU
- you need a permissively licensed library for commercial redistribution, since the license is non-standard

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, graphics, image-processing, simulation
- domain: computer-vision, graphics, machine-learning, deep-learning
- platform: python, cpp
- tags: 3d-gaussian-splatting, mesh-reconstruction, surface-reconstruction, neural-rendering, nerf, cvpr-2024, pytorch, 3d-reconstruction, blender-addon, gpu, linux

## Member repositories
- Anttwo/SuGaR (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:07.309605+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 2026-08-29T18:35:53.982729+00:00, confidence not recorded.
  - readme: https://github.com/Anttwo/SuGaR (fetched 2026-08-28T04:08:07.309605+00:00, sha 38980787bda6)
  - homepage: https://anttwo.github.io/sugar/ (fetched 2026-08-29T09:29:56.180545+00:00, sha 260c8bccd885)
- Data as of 2026-08-30T08:39:29.467469+00:00.