SAM 3D Objects
MetaSAM 3D Objects is Meta's model for turning an object in a single photograph into a full 3D shape with texture and layout. It was built for real-world pictures where objects are cluttered or partly hidden, and was released in November 2025 together with SAM 3D Body, a separate model for human body meshes.
SAM 3D Body recovers human body meshes, which is reconstruction rather than generation, so it is not part of this entry; the Segment Anything segmentation models are a separate product. Encoder weights were added in June 2026.
Openness
3 high confidence- weights
- open (checkpoints on the Hub behind a manual access request)
- data
- described (the README describes progressive training with a human-feedback data engine; no training set is released)
- code
- partial (inference code and a demo only; no training code)
- license
- SAM-License (the checkpoints and code, per the README and the LICENSE dated November 19, 2025)
SAM 3D Objects' code and weights are under Meta's SAM License, which allows commercial use and limits conduct and trade-controlled uses rather than the number of users or revenue. The weights need an approved access request on Hugging Face. Only inference code is published, and the training data is described but not released.
- https://huggingface.co/api/models/facebook/sam-3d-objects?expand[]=downloads&expand[]=likes&expand[]=cardData&expand[]=gated&expand[]=lastModified&expand[]=createdAt&expand[]=siblings recorded 2026-11-12
Hugging Face API record for facebook/sam-3d-objects: license other, gated "manual", checkpoint files under checkpoints/.
- https://ungh.cc/repos/facebookresearch/sam-3d-objects/files/main recorded 2026-11-12
Repository file list of 416 files: demo.py, inference requirements and the sam3d_objects package; no training script or training config.
- https://ungh.cc/repos/facebookresearch/sam-3d-objects/files/main/LICENSE recorded 2026-11-12
LICENSE body: "SAM License / Last Updated: November 19, 2025"; a "non-exclusive, worldwide, non-transferable and royalty-free limited license" to use, reproduce, distribute and modify the SAM Materials, including trained model weights.
- https://ungh.cc/repos/facebookresearch/sam-3d-objects/files/main/README.md recorded 2026-11-12
README: "The SAM 3D Objects model checkpoints and code are licensed under SAM License"; "using progressive training and a data engine with human feedback"; "11/19/2025 - Checkpoints Launched"; "06/01/2026 - Encoder weights are out."
Adoption
1 high confidenceAdoption is measured as Hugging Face downloads of facebook/sam-3d-objects, the only first-party copy; the separate SAM 3D Body checkpoints are left out.
- https://huggingface.co/api/models?author=facebook&search=sam-3d&sort=downloads&direction=-1&limit=100 recorded 2026-11-12
Listing of the facebook sam-3d repositories: sam-3d-objects 9243 downloads; sam-3d-body-dinov3 14359 and sam-3d-body-vith 1905 are the separate SAM 3D Body model.
Capability
3 medium confidenceSAM 3D Objects places in the upper half of the image-to-3D arena, level with InstantMesh and just behind Hunyuan3D-2 and 2.1. It is ranked only as a Gaussian-splat output, so the topology board does not list it.
- https://3d-arena-3d-arena.hf.space/api/leaderboard?vote_type=render recorded 2026-11-12
Render board of 24 entries: "SAM-3D-Objects-3DGS" rank 11, score 1268, 1423 votes; "Hunyuan3D-2" rank 8.
- https://3d-arena-3d-arena.hf.space/api/leaderboard?vote_type=topology recorded 2026-11-12
Topology board of 22 entries; no SAM 3D entry.
Verified 2026-11-12