Seminar: Dr. Robert Gens: How Machine Learning Benefits 3D Reconstruction

Data Science Fridays: Dr. Robert Gens

How Machine Learning Benefits 3D Reconstruction

Abstract: 3D reconstruction takes a collection of photographs or video and produces a 3D model. Classical stereo vision performs triangulation by assuming that a point on an object will appear the same from different viewpoints. This assumption doesn't hold for many real-world objects. In this talk I will cover the basics of classical stereo vision, its limitations, the ways that machine learning is being used to help, and research opportunities going forward.

Bio: Robert Gens has research interests in machine learning, deep learning, and computer vision. He focuses on developing algorithms to learn tractable and expressive deep models for vision and other real world data. He completed an S.B. in Electrical Engineering and Computer Science at the Massachusetts Institute of Technology in 2009, received an Outstanding Student Paper Award at NeurIPS 2012, and received his Ph.D. from the University of Washington in 2016, supported by the 2014 Google Ph.D. Fellowship in Deep Learning. He was a Research Scientist at Google from 2016 through 2019.

Ticket Information
https://forms.gle/iigpULteJ4RdPM2GA

Event Sponsor
Hawai'i Data Science Institute, Mānoa Campus

More Information
(808) 956-3503

Tweet