# facebookresearch/vggt-omega

[CVPR 2026 Oral] VGGT Omega

Repository: https://github.com/facebookresearch/vggt-omega
Canonical: https://ross.abutalabs.com/products/vggt-omega
Language: Python
License: NOASSERTION
License Family: other
Last push: 2026-08-18T16:15:25+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 7
- inputs: {"age_days": 111, "days_push": 15, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4165, forks 305 (observed 2026-08-28T04:08:37.645723+00:00)

## What it is
VGGT-Omega is a research library from Oxford VGG and Meta AI providing pretrained transformer models for 3D vision tasks such as camera pose estimation, depth estimation, and 3D reconstruction from images. It ships gated checkpoints on Hugging Face (access request required) plus a public demo space.

## Use cases
- estimate camera poses from a set of images
- reconstruct 3D scenes from photos
- predict depth maps from images
- run feed-forward 3D geometry models in python
- generate point clouds from multi-view images
- try a 3D vision foundation model demo

## When to choose
- you need state-of-the-art feed-forward 3D geometry predictions from images
- you want a research-grade model for camera pose, depth, or point map estimation
- you can obtain gated checkpoints and run GPU inference

## When to avoid
- you need a permissively licensed model for commercial products (license is non-standard and checkpoints are gated)
- you need CPU-only or lightweight inference
- you require guaranteed benchmark-accurate performance, since reported 1B results may be inflated by benchmark contamination

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, machine-learning, deep-learning, artificial-intelligence
- platform: python, cross-platform
- tags: 3d-reconstruction, visual-geometry, transformer, camera-pose-estimation, depth-estimation, point-cloud, research-model, cvpr, checkpoint-gated, gpu, linux

## Member repositories
- facebookresearch/vggt-omega (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:37.645723+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 2026-08-29T18:22:46.737028+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/vggt-omega (fetched 2026-08-28T04:08:37.645723+00:00, sha 77c1299f5da0)
- Data as of 2026-08-30T08:39:29.467469+00:00.