# lkeab/gaussian-grouping

[ECCV'2024] Gaussian Grouping for open-world Anything reconstruction, segmentation and editing.

Repository: https://github.com/lkeab/gaussian-grouping
Canonical: https://ross.abutalabs.com/products/gaussian-grouping
Homepage: https://arxiv.org/abs/2312.00732
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Last push: 2024-07-04T04:29:22+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": 1009, "days_push": 790, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1039, forks 73 (observed 2026-08-28T04:03:19.816340+00:00)

## What it is
Gaussian Grouping extends 3D Gaussian Splatting to jointly reconstruct and segment open-world 3D scenes by lifting 2D SAM masks into per-Gaussian identity encodings. It also provides a local Gaussian editing scheme supporting 3D object removal, inpainting, colorization, and scene recomposition.

## Use cases
- segment objects in 3D scenes from multi-view images
- remove large objects from reconstructed 3D scenes
- inpaint holes after 3D object removal
- reconstruct scenes with gaussian splatting and per-object masks
- colorize or recompose individual objects in a 3D scene
- evaluate open-world 3D segmentation on LERF-Mask dataset

## When to choose
- you need object-level segmentation on top of Gaussian Splatting reconstructions
- you want to edit (remove, inpaint, recolor) specific objects in a 3D scene
- you are reproducing or building on the ECCV 2024 Gaussian Grouping paper

## When to avoid
- you only need plain novel-view synthesis without segmentation
- you lack a CUDA GPU or cannot train Gaussian Splatting models
- you need a production-ready tool with polished UX rather than research code

## Facets
- artifact type: library
- maturity: stable
- function: image-processing, computer-vision, machine-learning, graphics
- domain: computer-vision, graphics, machine-learning
- platform: python
- tags: gaussian-splatting, 3d-segmentation, 3d-editing, sam, nerf, eccv-2024, scene-reconstruction, research-code, gpu, linux

## Member repositories
- lkeab/gaussian-grouping (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:19.816340+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 2026-08-30T07:03:37.575297+00:00, confidence not recorded.
  - readme: https://github.com/lkeab/gaussian-grouping (fetched 2026-08-28T04:03:19.816340+00:00, sha 7d653272e66a)
  - homepage: https://arxiv.org/abs/2312.00732 (fetched 2026-08-29T13:05:00.910393+00:00, sha 6bb0ba17aa06)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T13:05:00.931955+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T13:05:01.043573+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T13:05:01.079333+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T13:05:00.979199+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.