SAM 3D — Reconstruct Bodies & Objects from a Photo
3D Bodies and Objects from a Single Image
Meta's SAM 3D reconstructs 3D geometry from a single photo in two dedicated modes. Body mode recovers one or more people from the image, including their poses. Object mode reconstructs the item you name in a short text prompt. Both modes produce a downloadable GLB that you can preview interactively on this page — no multi-view capture or manual modeling required.
The two modes are optimized for different subjects. Body mode is built for people: upload a photo containing one or more people, and SAM 3D recovers their 3D body shape and pose. You can also include 3D keypoints in the model. Object mode is built for physical objects: upload a photo and name what you want to reconstruct with a short prompt, such as 'car', 'chair', or 'backpack'. SAM 3D then segments and reconstructs that object. You can fine-tune subject detection with the optional detection threshold, or export a textured GLB with textures and UV mapping baked into the file.
Because SAM 3D builds on Meta's Segment Anything family, it is especially good at isolating the right subject in a busy image before reconstruction. You don't need a clean studio shot or a turntable photo set — one everyday photo is enough to produce a 3D result you can rotate and inspect.
The workflow is simple. Choose Body or Object, upload your image, set your options, and generate the model. Then inspect it in the built-in interactive viewer: rotate, zoom, and check it from every angle. When it looks right, download the GLB and import it into your engine, renderer, or DCC tool. Every generation is also saved to your dashboard gallery so you can return to it later.
How to Generate a 3D Model with SAM 3D
Pick a Mode & Upload
Choose Image to Body for people, or Image to Object for things, then upload a single photo of your subject.
Set Options
For body, choose whether to include 3D keypoints. For object, describe what to reconstruct and adjust the detection threshold or textured-GLB option.
Generate & Download
Click Generate, then orbit and zoom the result in the interactive viewer. Download the GLB — every model is also saved to your dashboard gallery.
SAM 3D Technical Specifications
| Provider | Meta |
| Platform | Cloud API (hosted) |
| Input Modes | Image-to-body and image-to-object |
| Input | A single image |
| Body Mode | Recovers one or more human bodies with pose |
| Object Mode | Prompt-guided object reconstruction |
| Output Format | GLB |
| Preview | Interactive in-browser 3D viewer |
| Commercial Use | Supported |
Why Choose SAM 3D
Bodies and Objects
One model, two dedicated modes — recover human bodies with pose, or reconstruct everyday objects, both from a single photo.
Smart Subject Selection
Built on Meta's Segment Anything family, SAM 3D isolates the right subject in a busy image before reconstructing it. In object mode, your text prompt tells it which item to select.
One Photo, No Setup
No turntable, multi-view rig, or studio lighting needed — a single everyday image is enough to get a rotatable GLB you can preview and download.
SAM 3D vs Other Image-to-3D Models
| Feature | SAM 3D | Hyper3D Rodin v2.5 | Tripo3D H3.1 |
|---|---|---|---|
| Input | Single image | Up to 5 images, or text | Image, multiview or text |
| Specialty | Human bodies + objects | General objects + characters | General objects |
| Subject Selection | Segment Anything (prompt/mask) | Whole image | Whole image |
| Output | GLB | GLB | GLB |
| Best For | People & objects in everyday photos | Detail tiers & rig-ready poses | Faithful multi-angle reconstruction |
What Can You Create with SAM 3D
Human Avatars
Recover a posed 3D body from a photo for avatars, previs, and character reference.
Objects in Everyday Photos
Reconstruct an object from an everyday photo — no clean background or studio shot required.
AR & VR
Produce lightweight GLB assets that drop straight into AR experiences and VR scenes.
Product Visualization
Turn a single product photo into a 3D model for e-commerce and configurators.
Pose & Motion Reference
Use recovered bodies with 3D keypoints as pose and motion reference for animation and rigging.
Game Assets
Reconstruct props and characters from reference photos and bring them into your engine via GLB.
Related AI Models
Hunyuan 3D V3.1
Tencent image- & text-to-3D with PBR materials and GLB/OBJ export
Meshy v6
Image- & text-to-3D with mesh control and multi-format export
Tripo3D H3.1
Image-, multiview- & text-to-3D with quality control
Hyper3D Rodin v2.5
Image- & text-to-3D with quality tiers and rig-ready poses
Trellis 2
Microsoft TRELLIS image-to-3D with clean topology and resolution control
Frequently Asked Questions About SAM 3D
What does SAM 3D do?
SAM 3D reconstructs 3D geometry from a single image in two modes. Image-to-body recovers one or more human bodies with their pose; image-to-object reconstructs an object you specify with a short prompt. Both output a GLB you can preview and download.
What's the difference between body and object mode?
Body mode is built for people and recovers human body shape and pose from a photo, optionally including 3D keypoints. Object mode is built for things — you upload a photo, describe what to reconstruct (for example 'car'), and it segments and reconstructs that object.
How do I tell it which object to reconstruct?
In object mode, enter a short text prompt that names the object, such as 'chair' or 'backpack'. SAM 3D uses Meta's Segment Anything to isolate that subject before reconstructing it. You can also adjust the detection threshold to fine-tune subject selection.
Do I need multiple photos or a clean background?
No. SAM 3D works from a single everyday image and is designed to isolate the subject from a busy scene, so you don't need a turntable, a multi-view rig, or a studio backdrop.
What format do I get and can I preview it?
You receive a GLB file that works in web viewers, game engines, and AR applications. Before downloading it, you can rotate and zoom the model in the interactive browser preview to inspect it from every angle.
How is this different from Hyper3D Rodin v2.5 and Tripo3D H3.1?
SAM 3D specializes in reconstructing a selected subject — a human body or an object named in a prompt — from one everyday photo. It uses Meta's Segment Anything for subject selection. Hyper3D Rodin v2.5 accepts up to five images and offers quality tiers and rig-ready poses, while Tripo3D H3.1 adds multiview input and standard or detailed quality. Choose the model that best matches your source images and subject.