Preface

Developers working with 3D computer vision will be able to put their knowledge to work with this practical guide to 3D deep learning. The book provides a hands-on approach to implementation and associated methodologies that will have you up and running and productive in no time.

Complete with step-by-step explanations of essential concepts, practical examples, and self-assessment questions, you will begin by exploring state-of-the-art 3D deep learning.

You will learn about basic 3D mesh and point cloud data processing using PyTorch3D, such as loading and saving PLY and OBJfiles, projecting 3D points onto camera coordinates using perspective camera models or orthographic camera models, and rendering point clouds and meshes to images, among other things. You will also learn how to implement certain state-of-the-art 3D deep learning algorithms, such as differential rendering, NeRF, SynSin, and Mesh R-CNN because coding for these deep learning models becomes easier using the PyTorch3D library.

By the end of this book, you will be able to implement your own 3D deep learning models.