Reader small image

You're reading from  3D Deep Learning with Python

Product typeBook
Published inOct 2022
PublisherPackt
ISBN-139781803247823
Edition1st Edition
Right arrow
Authors (3):
Xudong Ma
Xudong Ma
author image
Xudong Ma

Xudong Ma is a Staff Machine Learning engineer with Grabango Inc. at Berkeley California. He was a Senior Machine Learning Engineer at Facebook(Meta) Oculus and worked closely with the 3D PyTorch Team on 3D facial tracking projects. He has many years of experience working on computer vision, machine learning and deep learning. He holds a Ph.D. in Electrical and Computer Engineering.
Read more about Xudong Ma

Vishakh Hegde
Vishakh Hegde
author image
Vishakh Hegde

Vishakh Hegde is a Machine Learning and Computer Vision researcher. He has over 7 years of experience in this field during which he has authored multiple well cited research papers and published patents. He holds a masters from Stanford University specializing in applied mathematics and machine learning, and a BS and MS in Physics from IIT Madras. He previously worked at Schlumberger and Matroid. He is a Senior Applied Scientist at Ambient.ai, where he helped build their weapon detection system which is deployed at several Global Fortune 500 companies. He is now leveraging his expertise and passion to solve business challenges to build a technology startup in Silicon Valley. You can learn more about him on his personal website.
Read more about Vishakh Hegde

Lilit Yolyan
Lilit Yolyan
author image
Lilit Yolyan

Lilit Yolyan is a machine learning researcher working on her Ph.D. at YSU. Her research focuses on building computer vision solutions for smart cities using remote sensing data. She has 5 years of experience in the field of computer vision and has worked on a complex driver safety solution to be deployed by many well-known car manufacturing companies.
Read more about Lilit Yolyan

View More author details
Right arrow

Summary

In this chapter, we presented a new way of looking at the object detection task. The 3D world requires solutions that work accordingly, and this is one of the first approaches toward that goal. We learned how Mesh R-CNN works by understanding the architecture and the structure of the model. We dove deeper into some interesting operations and techniques that are used in the model, such as graph convolutional networks, Cubify operations, the mesh predictor structure, and more. Finally, we learned how this model can be used in practice to detect objects on the image that the network has never seen before. We evaluated the results by rendering the 3D object.

Throughout this book, we have covered 3D deep learning concepts, from the basics to more advanced solutions. First, we learned about the various 3D data types and structures. Then, we delved into different types of models that solve different types of problems such as mesh detection, view synthesis, and more. In addition...

lock icon
The rest of the page is locked
Previous PageNext Chapter
You have been reading a chapter from
3D Deep Learning with Python
Published in: Oct 2022Publisher: PacktISBN-13: 9781803247823

Authors (3)

author image
Xudong Ma

Xudong Ma is a Staff Machine Learning engineer with Grabango Inc. at Berkeley California. He was a Senior Machine Learning Engineer at Facebook(Meta) Oculus and worked closely with the 3D PyTorch Team on 3D facial tracking projects. He has many years of experience working on computer vision, machine learning and deep learning. He holds a Ph.D. in Electrical and Computer Engineering.
Read more about Xudong Ma

author image
Vishakh Hegde

Vishakh Hegde is a Machine Learning and Computer Vision researcher. He has over 7 years of experience in this field during which he has authored multiple well cited research papers and published patents. He holds a masters from Stanford University specializing in applied mathematics and machine learning, and a BS and MS in Physics from IIT Madras. He previously worked at Schlumberger and Matroid. He is a Senior Applied Scientist at Ambient.ai, where he helped build their weapon detection system which is deployed at several Global Fortune 500 companies. He is now leveraging his expertise and passion to solve business challenges to build a technology startup in Silicon Valley. You can learn more about him on his personal website.
Read more about Vishakh Hegde

author image
Lilit Yolyan

Lilit Yolyan is a machine learning researcher working on her Ph.D. at YSU. Her research focuses on building computer vision solutions for smart cities using remote sensing data. She has 5 years of experience in the field of computer vision and has worked on a complex driver safety solution to be deployed by many well-known car manufacturing companies.
Read more about Lilit Yolyan