BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:Learning to See in 3D One Photon at a Time
X-WR-TIMEZONE:Pacific Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260722T134133Z
UID:tag:localist.com\,2008:EventInstance_52922211736902
DTSTART:20260529T210000Z
DTEND:20260529T220000Z
DESCRIPTION:Watch the recording.\n\nZoom link.\n\nDate: May 29\n\nTime: 2 p
 .m.\n\nLocation: KEC 1001\n\nAbstract: The next generation of versatile\, 
 dexterous AI agents must operate in unstructured\, real-world environments
  requiring high-speed 3D perception with millimeter precision. Current 3D 
 imaging techniques struggle to capture scene information when operating in
  challenging conditions\, such as high-speed motion and large illumination
  changes. In this talk\, I will introduce single-photon cameras\, an emerg
 ing image sensor technology capable of capturing scene information with pi
 cosecond temporal resolution and unprecedented dynamic range. While these 
 sensors offer extreme sensitivity\, they present a severe data bottleneck\
 , generating hundreds of gigabytes of raw photon data per second. I will d
 iscuss our lab’s recent work that bridges this gap through hardware-effi
 cient algorithms optimized for 3D computer vision tasks. We achieve ~100x 
 reduction in data bandwidth without sacrificing reconstruction fidelity in
  a variety of tasks\, such as 3D scene reconstruction and camera localizat
 ion and mapping.\n\nBio: Atul Ingle is an assistant professor in the Depar
 tment of Computer Science at Portland State University. He directs the Por
 tland State Computational Imaging Lab which designs next generation comput
 ational cameras and computer vision algorithms\, especially in resource-co
 nstrained applications. He received the PhD degree in Electrical Engineeri
 ng from University of Wisconsin-Madison in 2015. After several years in in
 dustrial R&D\, first at Philips Healthcare (2013\, 2014) and then at Fitbi
 t\, Inc. (2105–2017)\, he was a postdoc at UW-Madison from 2017-2021. Br
 oadly\, his research interests include computational imaging\, computer vi
 sion\, image sensors\, and signal processing. His work on single-photon 3D
  cameras received the Marr Prize (honorable mention) award at ICCV 2019 an
 d the ICCP Best Paper award in 2023.
GEO:44.567164;-123.278692
LOCATION:Kelley Engineering Center\, 1001
SUMMARY:Learning to See in 3D One Photon at a Time
URL;VALUE=URI:https://events.oregonstate.edu/event/learning-to-see-in-3d-on
 e-photon-at-a-time
CATEGORIES:Lecture or Presentation
END:VEVENT
END:VCALENDAR