BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Learning to See the World in 3D - Ayush Tewari (University of Camb
 ridge)
DTSTART:20250326T110000Z
DTEND:20250326T123000Z
UID:TALK229696@talks.cam.ac.uk
CONTACT:120952
DESCRIPTION:Humans can effortlessly construct rich mental representations 
 of the 3D world from sparse input\, such as a single image. This is a core
  aspect of intelligence that helps us understand and interact with our sur
 roundings and with each other. My research aims to build similar computati
 onal models–-artificial intelligence methods that can perceive propertie
 s of the 3D structured world from images and videos. Despite remarkable pr
 ogress in 2D computer vision\, 3D perception remains an open problem due t
 o some unique challenges\, such as limited 3D training data and uncertaint
 ies in reconstruction.\nMy goal will be to discuss these challenges and ex
 plain how my research addresses them by posing vision as an inverse proble
 m\, and by designing machine learning models with physics-inspired inducti
 ve biases.
LOCATION:Cambridge University Engineering Department\, CBL Seminar room BE
 4-38.
END:VEVENT
END:VCALENDAR