PyTorch3D

PyTorch3D provides efficient, reusable components for 3D Computer Vision research with PyTorch. Within FAIR, PyTorch3D has been used to power research projects such as Mesh R-CNN.

Key features include:

• Data structure for storing and manipulating triangle meshes
• Efficient operations on triangle meshes
• A differentiable mesh renderer

PyTorch3D is designed to integrate smoothly with deep learning methods for predicting and manipulating 3D data and therefore all operators in PyTorch3D are implemented using PyTorch tensors and can handle minibatches of hetereogenous data. They also can be differentiated and utilize GPUs for acceleration.