3DComputer vision

VGGT

Reconstructs a 3D scene from one, several or hundreds of photos in seconds: camera positions, depth and a point cloud. Best Paper at CVPR 2025.

Developer
Meta and the University of Oxford (VGG), USA / UK
First release
Mar 2025
Latest release
May 2026
Sizes
about 1.2B
License
Commercial use with conditionsVGGT-1B — CC-BY-NC 4.0; VGGT-1B-Commercial — own license, commercial use allowed (except military use); VGGT-Omega — non-commercial research
Running
On your own serverNeeds a GPU
Industries
Manufacturing and logistics, Media and production, Science and research
Deploy on your server Hugging Face GitHub

What it does

  • 3D model of a room or object from a photo series
  • Camera pose estimation for photogrammetry
  • Point cloud for measurements and comparison with the plan
  • Groundwork for 3D scenes and Gaussian splats

Where it is used

Construction and real estateManufacturing and geometry inspectionGame development and visual effects

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
no versions
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. VGGT-Omega
  2. VGGT-1B-Commercial
  3. VGGT-1B

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can VGGT be used in a commercial project?

With conditions. License: VGGT-1B — CC-BY-NC 4.0; VGGT-1B-Commercial — own license, commercial use allowed (except military use); VGGT-Omega — non-commercial research. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does VGGT need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does VGGT support Russian?

Language does not matter for this model: it does not work with text.

Where can I download VGGT and what does it cost?

The VGGT weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

3DMapAnythingMeta and Carnegie Mellon University · USACommercial use allowed

A single model builds a metric 3D reconstruction from photos, and uses camera, depth or pose data when available. One weights variant is under Apache 2.0.

Details3DPi3 (π³)Shanghai AI Lab · ChinaNon-commercial only

Reconstructs a 3D scene and camera positions from a set of photos or a video without relying on a "reference" frame. Pi3X gives smoother point clouds and approximate scale in meters.

Details3DDUSt3R / MASt3RNAVER LABS Europe · France (NAVER, South Korea)Non-commercial only

The family that started "single-pass" 3D reconstruction from a pair or set of photos without camera calibration. MASt3R added point matching and scale; MUSt3R and BLASt3R added video support.

Details

Source: github.com/facebookresearch/vggt. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.