3DComputer vision

Pi3 (π³)

Reconstructs a 3D scene and camera positions from a set of photos or a video without relying on a "reference" frame. Pi3X gives smoother point clouds and approximate scale in meters.

Developer
Shanghai AI Lab, China
First release
Jul 2025
Latest release
Dec 2025
Sizes
0.96B – 1.4B
License
Non-commercial onlyCode — BSD 3-Clause; Pi3 and Pi3X weights per the README — CC-BY-NC 4.0 (non-commercial use only)
Running
On your own serverNeeds a GPU
Industries
Science and research, Media and production
Deploy on your server Hugging Face GitHub

What it does

  • 3D scene reconstruction from video
  • Camera pose estimation from frames
  • Point clouds for research and prototypes

Where it is used

Research and R&DVisual effectsRobotics

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
no versions
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Pi3X
  2. Pi3

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can Pi3 (π³) be used in a commercial project?

No. License: Code — BSD 3-Clause; Pi3 and Pi3X weights per the README — CC-BY-NC 4.0 (non-commercial use only). A commercial product needs a different model or a separate agreement with the rights holder.

What hardware does Pi3 (π³) need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Pi3 (π³) support Russian?

Language does not matter for this model: it does not work with text.

Where can I download Pi3 (π³) and what does it cost?

The Pi3 (π³) weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

3DVGGTMeta and the University of Oxford (VGG) · USA / UKCommercial use with conditions

Reconstructs a 3D scene from one, several or hundreds of photos in seconds: camera positions, depth and a point cloud. Best Paper at CVPR 2025.

Details3DMapAnythingMeta and Carnegie Mellon University · USACommercial use allowed

A single model builds a metric 3D reconstruction from photos, and uses camera, depth or pose data when available. One weights variant is under Apache 2.0.

Details3DDUSt3R / MASt3RNAVER LABS Europe · France (NAVER, South Korea)Non-commercial only

The family that started "single-pass" 3D reconstruction from a pair or set of photos without camera calibration. MASt3R added point matching and scale; MUSt3R and BLASt3R added video support.

Details

Source: github.com/yyfz/Pi3. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.