---
title: "VGGT"
description: "VGGT from Meta AI (FAIR) / University of Oxford (VGG): 3d-reconstruction and 3dgs; Runner parity pending."
modelId: "vggt"
pageSource: authored
---

VGGT (Visual Geometry Grounded Transformer, CVPR 2025) is a feed-forward network that infers cameras, depth maps, point maps, and 3D point tracks from one to hundreds of views in a single pass — no per-scene optimization. In this catalog the in-tree two-stage 3DGS pipeline is registered, distinct from the vggt-omega and vggt-world entries.

<ModelPaperFigures modelId="vggt" locale="en" />

Project page: [vgg-t.github.io](https://vgg-t.github.io/). Code: [facebookresearch/vggt](https://github.com/facebookresearch/vggt).

The paper is [Paper](https://openaccess.thecvf.com/content/CVPR2025/papers/Wang_VGGT_Visual_Geometry_Grounded_Transformer_CVPR_2025_paper.pdf). Project page: [vgg-t.github.io](https://vgg-t.github.io). Code: [facebookresearch/vggt](https://github.com/facebookresearch/vggt).

<ModelCommandBuilder modelId="vggt" locale="en" />

## What it is for

Use `vggt` for catalog geometry inference. Choose it when the artifact is a reconstruction, not a generated video.

Per the CVPR 2025 paper, a large transformer alternates frame-wise and global attention over image tokens, with task-specific heads for cameras, depth, pointmaps, and tracking. Weights are apache-2.0 (facebookresearch/vggt); the recorded route builds 3DGS from VGGT geometry in two stages. It is published by Meta AI (FAIR) / University of Oxford (VGG).

Catalog tasks include 3d-reconstruction, 3dgs, and point-cloud. Documented outputs include point cloud.

Not [VGGT-World](/docs/guides/supported-models/vggt-world) and [Infinite VGGT](/docs/guides/supported-models/infinite-vggt).

## Runtime contract

Optional `input_path`, `interactions`, `fps`, `height`, and `width`.

CLI task profiles: `interactive-video`. WorldFoundry binds `VGGTPipeline`.

Family status: **Runner parity pending**.

Integration is **Runner parity pending**. For the verified scene-export route use vggt-omega; use this entry when you want the two-stage 3DGS pipeline over base VGGT geometry.

In-tree VGGT two-stage 3DGS pipeline is registered; distinct from vggt-omega and vggt-world catalog entries.

## Running in WorldFoundry

Launch `worldfoundry-eval run vggt --pipeline.task-profile interactive-video` to write geometry. The command builder above switches `--pipeline.task-profile` among recorded tasks and still emits `worldfoundry-eval run`.

The environment profile is not recorded.

Recorded weight repositories include `facebook/VGGT-1B`. Prepare the environment and check local assets with `bash scripts/inference/prepare_model_infer.sh vggt`. Add `--download` to fetch missing public checkpoints.

Status: **Runner parity pending**.

<ModelRelatedRecipes modelId="vggt" locale="en" />