# buaacyw/GaussianEditor

[CVPR 2024] GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting

Repository: https://github.com/buaacyw/GaussianEditor
Canonical: https://ross.abutalabs.com/products/gaussianeditor
Homepage: https://buaacyw.github.io/gaussian-editor/
Language: C++
License: NOASSERTION
License Family: other
Topics: 3d, generative-ai, cvpr2024
Last push: 2024-02-27T11:35:48+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": 1011, "days_push": 918, "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 1455, forks 73 (observed 2026-08-28T04:04:46.876678+00:00)

## What it is
GaussianEditor is a research application for fast, controllable 3D scene editing built on Gaussian Splatting, released as CVPR 2024 code. It uses Gaussian Semantic Tracing and hierarchical Gaussian splatting to edit, remove, or integrate objects in 3D scenes guided by 2D diffusion models in 2-7 minutes per edit.

## Use cases
- edit objects in a 3D gaussian splatting scene with text prompts
- remove an object from a 3D scene reconstruction
- add or integrate new objects into a 3D scene
- produce controllable high-resolution 3D edits faster than NeRF-based methods
- research 3D generative editing with 2D diffusion guidance

## When to choose
- you need precise, region-limited edits to a Gaussian Splatting 3D scene
- you want fast 3D editing (minutes, not hours) on a single GPU
- you are doing research on 3D generative editing or Gaussian Splatting

## When to avoid
- you need a production tool with a polished UI or commercial license (SLab license, non-standard)
- you lack a CUDA GPU with 10-20GB+ memory
- your scenes are mesh- or point-cloud-based rather than Gaussian Splatting

## Facets
- artifact type: application
- maturity: maintenance
- function: image-processing, machine-learning, graphics, stable-diffusion
- domain: computer-vision, graphics, deep-learning, artificial-intelligence
- platform: python, cpp
- tags: gaussian-splatting, 3d-editing, cvpr2024, nerf-alternative, research-code, generative-ai, linux, gpu, docker

## Member repositories
- buaacyw/GaussianEditor (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:46.876678+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 2026-08-30T04:35:38.466110+00:00, confidence not recorded.
  - readme: https://github.com/buaacyw/GaussianEditor (fetched 2026-08-28T04:04:46.876678+00:00, sha 61bec10a1668)
  - homepage: https://buaacyw.github.io/gaussian-editor/ (fetched 2026-08-29T11:44:39.734251+00:00, sha 8e5f18f3427c)
- Data as of 2026-08-30T08:39:29.467469+00:00.