Meta · Segment AnythingNEW

SAM 3D Online: Real Photos to 3D Models

SAM 3D is a pair of models Meta released on November 19, 2025. SAM 3D Objects rebuilds an object from one everyday photo, even when it is partly hidden or surrounded by clutter. SAM 3D Body does the same for people. On 3D AI Studio you can run SAM 3D Objects in the browser, with no GPU and no setup.

Works on messy photosNo GPU neededNo credit card

Updated November 2026

Choose a photo

Trusted by creators at top game studios and tech companies

Unreal Engine
Epic Games
Pixion
Lychee
Meta
Monume
Quick Turn Games
Polyworks
Tencent Games
NVIDIA
Avool
PitchDev Studios
Unreal Engine
Epic Games
Pixion
Lychee
Meta
Monume
Quick Turn Games
Polyworks
Tencent Games
NVIDIA
Avool
PitchDev Studios
Trustpilot
Rated Excellent/5

Three ways to use SAM 3D

They are not equal. One is a demo, one needs a data-center GPU, one runs in your browser and exports real files.

Demo

Segment Anything Playground

Meta's free web demo

  • Free, runs in the browser
  • Upload your own photo
  • Objects and people
  • Made for viewing results
  • No GLB for Blender, Unity or a slicer
Self-hosted

Run it yourself

GitHub code + Hugging Face weights

  • Full control and batch runs
  • Splat (.ply) and textured mesh output
  • Multi-object scenes
  • Linux and an NVIDIA GPU with 32 GB+ VRAM
  • Checkpoint access needs Meta's approval
Easiest

3D AI Studio

SAM 3D Objects in the browser

  • No GPU, no install
  • GLB, FBX, OBJ, STL, USDZ export
  • Same credits as every other model
  • Runs on credits (free ones every month)

How SAM 3D works: one object out of a messy photo

Most image-to-3D models want a single object on a clean background. SAM 3D starts from the kind of photo you actually have: a shelf, a floor, a room. Click the object to try the idea.

Click an object to select it
Messy playroom floor with toy blocks, a plush rabbit, a xylophone and a red toy fire truckTap the glowing dot
  1. Select the object

    Click the fire truck in the photo. SAM-style models take a click, a box or a text prompt.

  2. Isolate it

    Everything else in the frame is ignored. Hidden parts get filled in from context.

  3. Reconstruct in 3D

    A textured model you can rotate, export and use.

The isolated object shows up here
Isolated
The 3D model loads here. Drag to rotate.
3D model

Nov 2025Released

Meta, Segment Anything team

5:1Preference win rate

Meta's head-to-head tests

~1MReal photos annotated

~3.14M candidate meshes

32 GBVRAM to self-host

None needed in the browser

SAM 3D Objects vs SAM 3D Body

Same family, two different jobs. Most people searching for SAM 3D want Objects.

SAM 3D Objects

Things and scenes

GitHub
What it builds
Shape, texture and position of objects from one image
Input
A photo plus a mask of the object (from a click, a box or a SAM 3 text prompt)
Output
Gaussian splat (.ply) or textured mesh, placed where the object sits in the scene
Trained on
Almost 1 million real photos, ranked by people and fixed by 3D artists
Good for
Products, furniture, props, toys, rebuilding a room object by object

SAM 3D Body

People

GitHub
What it builds
Full-body 3D pose and body shape of a person
Input
A photo, optionally a mask or 2D keypoints to guide it
Output
A mesh in Meta's Momentum Human Rig (MHR) format, skeleton and soft tissue kept separate
Trained on
About 8 million curated images, picked for unusual poses and hard conditions
Good for
Pose capture from photos, sports and motion analysis, a starting point for avatars

Meta also publishes a notebook that lines up the output of both models in one frame of reference, so people and the objects around them can share one 3D scene. SAM 3D is also not the same as SAM 3, which only segments: SAM 3 finds and outlines objects, and SAM 3D turns them into 3D.

What SAM 3D does differently

Most 3D generators learned from synthetic assets on empty backgrounds. Meta went after real photos instead.

Trained on real photos

Annotators ranked meshes that several models proposed for each photo, and the hardest cases went to 3D artists. That produced 3D labels for almost a million everyday images.

Copes with clutter and occlusion

Small objects, odd angles and things half behind other things are the normal case for SAM 3D. Context in the photo fills the gaps the pixels leave.

Knows where the object sits

SAM 3D Objects predicts each object's pose and position, so several objects from one photo can be put back together as a 3D scene you can walk the camera around.

Promptable like the rest of SAM

Pick the object with a click, a box or a mask from SAM 3. SAM 3D Body also accepts 2D keypoints when a pose is ambiguous.

Fast at inference

Meta says shortcuts in the diffusion step bring full textured reconstructions down to a few seconds on its hardware, quick enough for robotics use.

Open and benchmarked

Code, weights, the SA-3DAO artist dataset and a public leaderboard are all out. Encoder weights and the leaderboard followed in June 2026.

Where SAM 3D falls short

Most of these come straight from Meta's own release notes.

Moderate resolution

Fine detail gets lost on complex objects. Meta's example: a whole person rebuilt with Objects can come out distorted.

One object at a time

Objects are predicted separately. The model does not reason about contact, so objects in a rebuilt scene can float or overlap.

Body handles one person at a time

Groups and person-object interaction are not modelled together, and hands trail specialised hand-pose models.

Heavy to self-host

Linux, 32 GB of VRAM, a fiddly CUDA environment and an approval step before you can download the weights.

The practical upshot: SAM 3D is the right tool when the photo is messy and you cannot reshoot it. When you have a clean shot and need maximum detail, a dedicated image-to-3D model still wins.

SAM 3D vs Prism 3.1 vs Hunyuan3D 3.1 vs TRELLIS 2

All four run on 3D AI Studio. Pick per photo, not per brand.

FeatureSAM 3D ObjectsPrism 3.1Hunyuan3D 3.1TRELLIS 2
Made byMeta3D AI StudioTencentMicrosoft
Best inputObject inside a real, busy photoClean photo of one objectClean image or textClean image
Clutter and occlusionMain strengthCut it out firstCut it out firstCut it out first
Scene layoutYes, pose and positionNoNoNo
DetailModerate (Meta's words)HighHigh, watertightGood, fast drafts
OutputTextured GLBTextured GLBGLB, 4K PBRGLB, PBR
Pick it whenThe photo is messy and can't be reshotYou have a clean photoYou need a print-ready meshYou want cheap, fast drafts

Model pages: Prism 3.1, Hunyuan3D 3.1, TRELLIS 2. Prices for every model are in the pricing comparison.

Which model should you use?

Start from the photo you have and what the model is for.

My photo is cluttered and I can't reshoot it

SAM 3D Objects. This is the photo it was built for.

I have a clean photo of one object

Prism 3.1, the default in Image to 3D, gives you more detail when nothing is in the way.

I want to 3D print it

Hunyuan3D 3.1 for watertight meshes, Hitem3D 2.1 for miniature-level detail.

I want the whole room, not one object

Image to Gaussian Splat works now. SAM 3D's multi-object scenes are the other route.

I need an animated character

SAM 3D Body gives you pose, not a game character. Generate the character in Image to 3D, then rig it.

How to use SAM 3D on 3D AI Studio

Four steps, a few minutes, nothing to install.

  1. 01

    Open Image to 3D

    Go to Image to 3D on 3D AI Studio and pick SAM 3D Objects in the model list.

  2. 02

    Upload your photo

    Use a photo that shows the object, even a busy everyday one. If several objects compete for attention, crop around the one you want.

  3. 03

    Generate

    SAM 3D rebuilds the object in 3D, including the parts that other things hide in the photo. Rotate it in the viewer to check it.

  4. 04

    Export

    Download the GLB, or convert it to FBX, OBJ, STL or USDZ for Blender, Unity, Unreal, a slicer or AR.

Optional: isolate the object first

When the object is tiny in the frame or mostly covered, cutting it out first gives the model more to work with. Use Remove Background for clear subjects, or Nano Banana 2.1 Edit when parts are hidden.

Original playroom photo with the toy fire truck among blocks and toys
Before: the photo
The fire truck isolated on white after one Nano Banana 2.1 Edit
After one edit
Edit prompt we used

Isolate only the red wooden toy fire truck from this photo. Show the complete fire truck alone, centered, on a plain pure white background, same three-quarter view, same colors, ladder and wheels. Reconstruct any hidden parts.

Ask the edit model to keep the same view. The 3D model reads the angle from the image, so a cut-out that matches the original photo gives you a model that matches it too.

License and commercial use

SAM 3D code and weights

Released under Meta's SAM License. Commercial use is allowed, with conditions that include export and trade-control rules. Read the license before you ship.

MHR body model

The Momentum Human Rig that SAM 3D Body outputs is released under a permissive commercial license.

Models you make on 3D AI Studio

Paid plans include commercial usage rights for every model you generate, whichever engine made it.

Sources: Meta's announcement, SAM 3D Objects and SAM 3D Body on GitHub, Hugging Face, the paper.

SAM 3D next to every other top model

One credit balance covers SAM 3D and all of these. Switch models per generation.

The full lineup is on the Models page.

Frequently asked questions

What people ask about SAM 3D

Try SAM 3D now

Upload an everyday photo and get a 3D model in minutes. Free credits every month, no credit card.

Want splats instead of meshes?

Image to Gaussian Splat turns a single image into a splat scene in the browser, the same kind of output SAM 3D saves locally.

Need more detail from a clean photo?

Prism 3.1 is the default photo reconstruction model on 3D AI Studio, built for detail and texture fidelity when the object is clearly visible.

What every AI 3D generator costs

Plans, credits and the real price per model across Meshy, Tripo, Rodin, Hitem3D and 3D AI Studio, checked this month.