VGGT
Feed-forward transformer that infers full 3D scene geometry from one or many views.
About
VGGT (Visual Geometry Grounded Transformer), from Meta FAIR and published at CVPR 2025, directly infers all key 3D attributes of a scene — camera parameters, point maps, depth maps, and 3D point tracks — from one, a few, or hundreds of views in a single forward pass, replacing the slow optimization pipelines 3D vision usually depends on. The authors report state-of-the-art results across camera estimation, multi-view depth, dense reconstruction, and point tracking.
Code and the VGGT-1B weights are publicly released through the facebookresearch/vggt repository and Hugging Face, and the pretrained backbone also transfers well to downstream tasks like novel view synthesis. Confirm the license on the repo before commercial use.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Paper-reported: state-of-the-art on camera parameter estimation, multi-view depth estimation, dense point cloud reconstruction, and 3D point tracking (CVPR 2025).
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 7/10
Scored 7/10 (metrics tier, metrics-v1). Evidence: CVPR 2025 peer-reviewed; strong 3D-vision results.; Public repo and VGGT-1B weights; day of release not pinned.. License: Code and models publicly released; confirm license on the facebookresearch/vggt repo before commercial use..
How the trust score is built
Full methodology →- Adoption · stars/downloads, log-scaled vs peers
- 7.0/10
- Maintenance · recency, releases, issue load
- 7.0/10
- Openness · license + docs
- 7.0/10
- Manual review · sanity read + red-flag check
- 7.0/10
- · CVPR 2025 peer-reviewed; strong 3D-vision results.
- · Public repo and VGGT-1B weights; day of release not pinned.