Building 3D deep learning models with PyTorch3D

By Kayleigh Shooter

 In the same way that Torchvision and Detectron2 offer highly optimized libraries for 2D computer vision, PyTorch3D offers capabilities that support 3D data. Our open source library for 3D deep learning includes support for easy batching of heterogeneous meshes and point clouds, optimized implementations of common 3D operators such as Chamfer Loss and Graph Conv, as well as a modular, differentiable renderer for point clouds and meshes. We’re already using PyTorch3D at Facebook for research projects such as Mesh R-CNN and SynSin.
 

Share

Featured Videos

View all
Featured

Magnús Kristinsson, atNorth DCs CEO, on investment & growth

atNorth CEO Magnús Kristinsson talks about their DC expansion into new markets and the investments and underlying vision that has driven AN’s evolution

Technology

Alder Hey: innovating to advance children’s healthcare

AI Strategy

DXC Technology: Autonomous driving solutions for the future

AI Strategy

AIOPS.D: Enterprise Autonomous Operations in the AI Age