The Machine Learning Center at Georgia Tech presents a seminar by Ashwin Swaninathan of MagicLeap. Magic Leap is a startup company that is working on head-mounted virtual reality retinal display. The event will be held in the Marcus Nanotechnology from 2:00-3:00 p.m. and is open to the public.
This talk presents the importance of Computer Vision and Deep learning techniques in making Magic Leap an effective spatial computing platform. The four fundamental modalities are introduced: head pose tracking, world reconstruction, eye tracking, and hand tracking; emphasizing on the two main general themes: Understanding the world (spatial localization, environment mapping) and Understanding user’s intent (eye, gaze, and hands). The talk will provide a deep dive into the main modalities along with key challenges and open problems. We will go over some technical challenges that our team of researchers and engineers are tacking to make computer vision work for see-through wearable Mixed Reality device. We will start with an overview of the past 5 years of development in inside-out pose estimation (Visual Inertial Odometry), scene reconstruction, eye tracking, and sensor calibration and then dive into the long list of technical challenges that are left to solve.
Ashwin Swaminathan is part of computer vision team at Magic Leap where he leads a team researching on simultaneous localization and mapping, object recognition, visual inertial odometry, and scene semantics.
Prior to joining Magic Leap, he was with Qualcomm Research in San Diego from 2008 to 2015. At Qualcomm Research, he was involved in various computer vision and machine learning projects for applications in augmented reality and context-aware computing on mobile phones. In addition, he was involved in Qualcomm’s efforts in robotics and drones.
Ashwin Swaminathan holds a Ph.D. from the University of Maryland, College Park where he conducted research on several topics in image processing, multimedia forensics, security and watermarking.
Ashwin holds 30+ patents in the field of computer vision, machine learning and Augmented Reality. He has authored 7 journal papers, 30+ conference papers with a combined 3200+ citations.
For scheduling information please contact Zsolt Kira at Zsolt.Kira@gtri.gatech.edu