Welcome to TensorFlow3d Transforms’s documentation!

https://img.shields.io/github/stars/Rishit-dagli/3d-transforms?style=social.svg https://img.shields.io/twitter/url?style=social&url=https%3A%2F%2Fgithub.com%2FRishit-dagli%2F3d-transforms.svg

TensorFlow3d Transforms is a library to easily make 3D transformations and work with 3D data. This library originally started as a few functions here and there for my own work which I then turned into a library.

TensorFlow3d Transforms is designed to integrate smoothly with deep learning methods for predicting and manipulating 3D data. For this reason, all operators in TensorFlow3d Transforms:

  • Are implemented using TensorFlow tensors

  • Can handle minibatches of hetereogenous data

  • Can be differentiated

  • Can utilize GPUs for acceleration

Much inspiration for this project is taken from PyTorch3D

Indices and tables