# Meta's SAM 3D Body Reconstructs Human Pose From Images

> The new model recovers full 3D human mesh and pose from a single photo, extending Meta's Segment Anything lineage into 3D.

Published by The Open Weights on Nov 17, 2025. Canonical: https://theopenweights.com/news/sam-3d-body-68jp

## Key facts

- Company: Meta AI
- Model: SAM 3D Body
- Version: 1
- Category: Text → 3D
- Modalities: Text → 3D
- License: Other (Open weights, commercial use allowed)
- Significance: notable
- Published: 2025-11-17
- Last verified: 2026-11-10
- Hugging Face: https://huggingface.co/facebook/sam-3d-body-dinov3
- Canonical URL: https://theopenweights.com/news/sam-3d-body-68jp

Meta AI has released **SAM 3D Body**, a model that reconstructs a 3D human mesh and estimates body pose from ordinary 2D images. Published on [Hugging Face](https://huggingface.co/facebook/sam-3d-body-dinov3), the release extends Meta's Segment Anything family — long associated with 2D segmentation — into the harder territory of three-dimensional human reconstruction.

Human mesh recovery turns a flat photo into a posed, volumetric model of a person, capturing limb positions and body shape. That capability underpins a range of applications, from motion capture and avatars to AR, fitness, and robotics perception. The model name references **DINOv3**, Meta's self-supervised vision backbone, suggesting the system leans on strong learned image features to anchor its 3D predictions.

## Why it matters

Single-image 3D reconstruction has historically required specialized rigs or multi-camera setups. Bringing it to a single photo, with an openly available checkpoint, lowers the barrier for researchers and developers who want to experiment without heavy capture infrastructure.

- Recovers full 3D body mesh from a single image
- Handles pose estimation alongside shape
- Builds on Meta's DINOv3 vision features

The model is distributed under a custom license, so teams planning commercial use should review the terms on the model card before building on it. As an initial release, it sets a baseline that Meta and the wider community can iterate on.

## Get the model

- [Hugging Face](https://huggingface.co/facebook/sam-3d-body-dinov3)

## Sources

- [facebook/sam-3d-body-dinov3](https://huggingface.co/facebook/sam-3d-body-dinov3) — Hugging Face, Nov 17, 2025

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Meta's SAM 3D Body Reconstructs Human Pose From Images", The Open Weights, Nov 17, 2025, https://theopenweights.com/news/sam-3d-body-68jp