# GAP-LAB-CUHK-SZ/gaustudio

A Modular Framework for 3D Gaussian Splatting and Beyond

Repository: https://github.com/GAP-LAB-CUHK-SZ/gaustudio
Canonical: https://ross.abutalabs.com/products/gaustudio
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: 3d-reconstruction, 3dgs, gaussian-splatting, multi-view-reconstruction, nerf, pytorch, surface-reconstruction
Last push: 2025-11-05T08:26:09+00:00

## Health v2 (maintenance only)
Score: 49/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 50, release rhythm 35, longevity 70
- inputs: {"age_days": 991, "days_push": 301, "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 1762, forks 101 (observed 2026-08-28T04:05:32.770519+00:00)

## What it is
GauStudio is a modular PyTorch framework for 3D Gaussian Splatting (3DGS) research and development, supporting novel view synthesis, 3D reconstruction, and surface reconstruction. It also ships curated COLMAP-format datasets with normal annotations and LoFTR-based point cloud initialization.

## Use cases
- train and evaluate 3d gaussian splatting models
- novel view synthesis from multi-view images
- surface reconstruction from photos
- convert nerf synthetic datasets to colmap format
- research on 3dgs methods with a modular codebase
- reconstruct indoor scenes with normal annotations

## When to choose
- you need a modular, extensible framework for 3DGS research
- you want ready-to-use COLMAP-format benchmark datasets
- you need GPU-accelerated 3D reconstruction with PyTorch

## When to avoid
- you need a polished end-user 3D scanning application
- you work on Windows without troubleshooting tolerance
- you lack a CUDA-capable NVIDIA GPU with at least 6GB VRAM

## Facets
- artifact type: framework
- maturity: active
- function: machine-learning, graphics, simulation, image-processing, data-science
- domain: computer-vision, graphics, machine-learning, deep-learning
- platform: python, cross-platform
- tags: 3d-gaussian-splatting, 3dgs, nerf, 3d-reconstruction, surface-reconstruction, pytorch, multi-view-reconstruction, colmap, linux, gpu

## Member repositories
- GAP-LAB-CUHK-SZ/gaustudio (main) score 49

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:32.770519+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 2026-08-30T03:26:48.017297+00:00, confidence not recorded.
  - readme: https://github.com/GAP-LAB-CUHK-SZ/gaustudio (fetched 2026-08-28T04:05:32.770519+00:00, sha d123619e6080)
- Data as of 2026-08-30T08:39:29.467469+00:00.