Home

Awesome

<img src="https://raw.githubusercontent.com/facebookresearch/pytorch3d/main/.github/pytorch3dlogo.png" width="900"/>

CircleCI Anaconda-Server Badge

Introduction

PyTorch3D provides efficient, reusable components for 3D Computer Vision research with PyTorch.

Key features include:

PyTorch3D is designed to integrate smoothly with deep learning methods for predicting and manipulating 3D data. For this reason, all operators in PyTorch3D:

Within FAIR, PyTorch3D has been used to power research projects such as Mesh R-CNN.

See our blog post to see more demos and learn about PyTorch3D.

Installation

For detailed instructions refer to INSTALL.md.

License

PyTorch3D is released under the BSD License.

Tutorials

Get started with PyTorch3D by trying one of the tutorial notebooks.

<img src="https://raw.githubusercontent.com/facebookresearch/pytorch3d/main/.github/dolphin_deform.gif" width="310"/><img src="https://raw.githubusercontent.com/facebookresearch/pytorch3d/main/.github/bundle_adjust.gif" width="310"/>
Deform a sphere mesh to dolphinBundle adjustment
<img src="https://raw.githubusercontent.com/facebookresearch/pytorch3d/main/.github/render_textured_mesh.gif" width="310"/><img src="https://raw.githubusercontent.com/facebookresearch/pytorch3d/main/.github/camera_position_teapot.gif" width="310" height="310"/>
Render textured meshesCamera position optimization
<img src="https://raw.githubusercontent.com/facebookresearch/pytorch3d/main/.github/pointcloud_render.png" width="310"/><img src="https://raw.githubusercontent.com/facebookresearch/pytorch3d/main/.github/cow_deform.gif" width="310" height="310"/>
Render textured pointcloudsFit a mesh with texture
<img src="https://raw.githubusercontent.com/facebookresearch/pytorch3d/main/.github/densepose_render.png" width="310"/><img src="https://raw.githubusercontent.com/facebookresearch/pytorch3d/main/.github/shapenet_render.png" width="310" height="310"/>
Render DensePose dataLoad & Render ShapeNet data
<img src="https://raw.githubusercontent.com/facebookresearch/pytorch3d/main/.github/fit_textured_volume.gif" width="310"/><img src="https://raw.githubusercontent.com/facebookresearch/pytorch3d/main/.github/fit_nerf.gif" width="310" height="310"/>
Fit Textured VolumeFit A Simple Neural Radiance Field
<img src="https://raw.githubusercontent.com/facebookresearch/pytorch3d/main/.github/fit_textured_volume.gif" width="310"/><img src="https://raw.githubusercontent.com/facebookresearch/pytorch3d/main/.github/implicitron_config.gif" width="310" height="310"/>
Fit Textured Volume in ImplicitronImplicitron Config System

Documentation

Learn more about the API by reading the PyTorch3D documentation.

We also have deep dive notes on several API components:

Overview Video

We have created a short (~14 min) video tutorial providing an overview of the PyTorch3D codebase including several code examples. Click on the image below to watch the video on YouTube:

<a href="http://www.youtube.com/watch?v=Pph1r-x9nyY"><img src="http://img.youtube.com/vi/Pph1r-x9nyY/0.jpg" height="225" ></a>

Development

We welcome new contributions to PyTorch3D and we will be actively maintaining this library! Please refer to CONTRIBUTING.md for full instructions on how to run the code, tests and linter, and submit your pull requests.

Development and Compatibility

Contributors

PyTorch3D is written and maintained by the Facebook AI Research Computer Vision Team.

In alphabetical order:

Citation

If you find PyTorch3D useful in your research, please cite our tech report:

@article{ravi2020pytorch3d,
    author = {Nikhila Ravi and Jeremy Reizenstein and David Novotny and Taylor Gordon
                  and Wan-Yen Lo and Justin Johnson and Georgia Gkioxari},
    title = {Accelerating 3D Deep Learning with PyTorch3D},
    journal = {arXiv:2007.08501},
    year = {2020},
}

If you are using the pulsar backend for sphere-rendering (the PulsarPointRenderer or pytorch3d.renderer.points.pulsar.Renderer), please cite the tech report:

@article{lassner2020pulsar,
    author = {Christoph Lassner and Michael Zollh\"ofer},
    title = {Pulsar: Efficient Sphere-based Neural Rendering},
    journal = {arXiv:2004.07484},
    year = {2020},
}

News

Please see below for a timeline of the codebase updates in reverse chronological order. We are sharing updates on the releases as well as research projects which are built with PyTorch3D. The changelogs for the releases are available under Releases, and the builds can be installed using conda as per the instructions in INSTALL.md.

[Oct 31st 2023]: PyTorch3D v0.7.5 released.

[May 10th 2023]: PyTorch3D v0.7.4 released.

[Apr 5th 2023]: PyTorch3D v0.7.3 released.

[Dec 19th 2022]: PyTorch3D v0.7.2 released.

[Oct 23rd 2022]: PyTorch3D v0.7.1 released.

[Aug 10th 2022]: PyTorch3D v0.7.0 released with Implicitron and MeshRasterizerOpenGL.

[Apr 28th 2022]: PyTorch3D v0.6.2 released

[Dec 16th 2021]: PyTorch3D v0.6.1 released

[Oct 6th 2021]: PyTorch3D v0.6.0 released

[Aug 5th 2021]: PyTorch3D v0.5.0 released

[Feb 9th 2021]: PyTorch3D v0.4.0 released with support for implicit functions, volume rendering and a reimplementation of NeRF.

[November 2nd 2020]: PyTorch3D v0.3.0 released, integrating the pulsar backend.

[Aug 28th 2020]: PyTorch3D v0.2.5 released

[July 17th 2020]: PyTorch3D tech report published on ArXiv: https://arxiv.org/abs/2007.08501

[April 24th 2020]: PyTorch3D v0.2.0 released

[March 25th 2020]: SynSin codebase released using PyTorch3D: https://github.com/facebookresearch/synsin

[March 8th 2020]: PyTorch3D v0.1.1 bug fix release

[Jan 23rd 2020]: PyTorch3D v0.1.0 released. Mesh R-CNN codebase released: https://github.com/facebookresearch/meshrcnn