facebookresearch /pytorch3d
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
★ 9,999⑂ 1,483👁 148⑃ 231● 1,695▤ 20
+2
Daily
9,999
stars
1,483
forks
148
watchers
231
prs
1,695
issues
20
releases
README
Introduction PyTorch3D provides efficient, reusable components for 3D Computer Vision research with PyTorch. Key features include: - Data structure for storing and manipulating triangle meshes - Efficient operations on triangle meshes (projective transformations, graph convolution, sampling, loss functions) - A differentiable mesh renderer - Implicitron, see its README, a framework for new-view synthesis via implicit representations. (blog post) PyTorch3D is designed to integrate smoothly with deep learning methods for predicting and manipulating 3D data. For this reason, all operators in PyTorch3D: - Are implemented using PyTorch tensors - Can handle minibatches of hetereogenous data - Can be differentiated - Can utilize GPUs for acceleration 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. ||| |:-----------------------------------------------------------------------------------------------------------:|:--------------------------------------------------:| | Deform a sphere mesh to dolphin| Bundle adjustment | | | |:------------------------------------------------------------:|:--------------------------------------------------:| | Render textured meshes| Camera position optimization| | | |:------------------------------------------------------------:|:--------------------------------------------------:| | Render textured pointclouds| Fit a mesh with texture| | | |:------------------------------------------------------------:|:--------------------------------------------------:| | Render DensePose data| Load & Render ShapeNet data| | | |:------------------------------------------------------------:|:--------------------------------------------------:| | Fit Textured Volume| Fit A Simple Neural Radiance Field| | | |:------------------------------------------------------------:|:--------------------------------------------------:| | Fit Textured Volume in Implicitron| Implicitron Config System| Documentation Learn more about the API by reading the PyTorch3D documentation. We also have deep dive notes on several API components: - Heterogeneous Batching - Mesh IO - Differentiable Rendering 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: 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 - main branch: actively developed, without any guarantee, Anything can be
Top issues
#561NaN when using MeshRasterizer32 comments · 2021-02-12#1401Repeatedly breaking fbapipublicfiles (central list)22 comments · 2022-12-19#1734 ERROR: Failed building wheel for pytorch3d18 comments · 2024-02-20#1157🐛 Rasterizer returns correct zbuf but empty dists, and z_near doesnt work12 comments · 2022-04-05#868Errors in NeRF implementation12 comments · 2021-10-06#223Cast shadows12 comments · 2020-06-04#1518Any Support for CUDA version (12.1)?11 comments · 2023-04-22#1352PerspectiveCameras issue with PulsarPointsRenderer11 comments · 2022-10-05
Discussions
#2066General stat of pytorch3d1 comments · 2026-11-03#2024pytorch3d is featured on Shypd — 80K+ AI tools0 comments · 2026-03-30#1999Optimizing parametric hand model and object mesh positions and orientations using ID masks0 comments · 2025-09-02#1950Bundle Adjustment Tutorial contribution0 comments · 2025-02-11#1942Iou calculate for 2d polygon0 comments · 2025-01-27#1941Depth differentiability3 comments · 2025-01-24#1910Texels to pixel contribution2 comments · 2024-11-04#1895How to install pytorch3d for pytorch 2.4.1 with cu1180 comments · 2024-10-15
Latest release
Version 0.7.9 v0.7.9 2025-11-28Miscellaneous fixes and improvements.