# MIT-SPARK/VGGT-SLAM

VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold

Repository: https://github.com/MIT-SPARK/VGGT-SLAM
Canonical: https://ross.abutalabs.com/products/vggt-slam
Language: Python
License: BSD-2-Clause
License Family: permissive
Topics: computer-vision, slam, vggt, vggt-slam
Last push: 2026-06-29T14:33:30+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 90, release rhythm 35, longevity 32
- inputs: {"age_days": 457, "days_push": 65, "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 1102, forks 118 (observed 2026-08-28T04:03:35.945304+00:00)

## What it is
VGGT-SLAM is a dense RGB SLAM system that performs real-time feed-forward 3D scene reconstruction, optimizing on the SL(4) manifold using the VGGT feed-forward model. It supports incremental map construction with visualization and optional open-set 3D object detection.

## Use cases
- reconstruct 3D scenes from a folder of RGB images
- run dense visual SLAM in real time
- build incremental 3D maps with loop closure
- detect open-set 3D objects from text queries
- evaluate dense SLAM on benchmark datasets

## When to choose
- you need dense 3D reconstruction from plain RGB images without depth sensors
- you want real-time feed-forward SLAM with loop closure
- you need 3D object detection integrated into mapping

## When to avoid
- you need LiDAR or depth-sensor-based SLAM
- you lack a GPU or cannot install large vision models
- you need a lightweight sparse visual odometry solution

## Facets
- artifact type: library
- maturity: active
- function: computer-vision, machine-learning, graphics, simulation
- domain: computer-vision, robotics, deep-learning
- platform: python
- tags: slam, 3d-reconstruction, vggt, dense-mapping, simultaneous-localization-and-mapping, scene-reconstruction, open-set-detection, linux, gpu

## Member repositories
- MIT-SPARK/VGGT-SLAM (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:35.945304+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 2026-08-30T06:45:36.179177+00:00, confidence not recorded.
  - readme: https://github.com/MIT-SPARK/VGGT-SLAM (fetched 2026-08-28T04:03:35.945304+00:00, sha 9bb46d32eeed)
- Data as of 2026-08-30T08:39:29.467469+00:00.