Ashwin Swaminathan

Currently, I am a Senior Director, Perception at Magic Leap, Inc. Here, I lead the World sensing team that includes critical Perception components such as SLAM, Online Calibration, World Reconstruction, Object Recognition and Scene Understanding. I am responsible for defining the sensor configuration, compute architecture, and algorithms for World sensing stack for ML2 working with the team.

I also serve as the engineering lead for Magic Leap’s AR-cloud solution for Perception that includes:

• Content Persistence

• Multi-user sharing

• Large Scale Mapping

• World understanding and

• AR Cloud

My team and I are responsible for end-to-end development including algorithm research, architecture design, engineering, prototype, and integration.

Check out our recent feature releases on ML1:

• Persistence and sharing features in MagicVerse SDK for ML1 Lumin OS (May 2019)

• XRKit on iOS and Android (March 2020), and

• Object recognition for generic objects with 3D bounding boxes (March 2020).

Previously, I was a Senior Staff Engineer/Manager at Qualcomm Research where I was involved in building computer vision and machine learning algorithms for Qualcomm Snapdragon chipsets for various usecases - Augmented Reality, Virtual Reality, and Drones. I also lead various academic research collaborations within Qualcomm and serve as a member of the Qualcomm patent review board.

Prior to joining Qualcomm Research, I obtained my Bachelors degree in Electrical Engineering from the Indian Institute of Technology, Madras and my M.S. and Ph.D. degree from the Department of Electrical and Computer Engineering at the University of Maryland, College Park. My thesis was on Multimedia Forensics via Intrinsic and Extrinsic Fingerprints and this work focuses on various problems related to information security and multimedia forensics.

During my days as a Ph.D. student at UMD, I did internships with the Mobile and Media Systems Lab at Hewlett Packard, Palo Alto, CA (2006) on projects related to Digital Rights Management and with the Machine learning and Applied Statistics Lab at Microsoft Research, Redmond, WA (2007).