BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Recreating the Physical Natural World from Images - Dr Elliott Wu 
 - Department of Engineering\, University of Cambridge
DTSTART:20250521T140500Z
DTEND:20250521T145500Z
UID:TALK229606@talks.cam.ac.uk
CONTACT:Ben Karniely
DESCRIPTION:For centuries\, unraveling the mysteries of nature through the
  lens of physics has captivated countless scientists. Today\, generative A
 I models excel at reproducing visual worlds in pixels\, but still struggle
  with basic physical concepts such as 3D shape\, motion\, material\, and l
 ighting---key elements that connect computer vision to a wide range of rea
 l-world engineering applications\, including interactive VR\, robotics\, b
 iology\, and medical analysis. The main challenge arises from the difficul
 ty of collecting large-scale physical measurements for training machine le
 arning models.\n\nIn this talk\, I will discuss an alternative unsupervise
 d approach based on inverse rendering\, which enables machine learning mod
 els to learn explicit physical representations from raw\, unstructured ima
 ge data\, such as Internet photos and videos. This approach thus circumven
 ts the need for any direct supervision\, allowing us to model a wide varie
 ty of 3D objects in nature\, including diverse wildlife\, using only casua
 lly recorded imagery. The resulting model can generate physically-grounded
  3D assets with controllable animations instantly\, ready for downstream r
 endering and analysis. The papers presented can be found at: https://ellio
 ttwu.com/.\n\n\nLink to join virtually: https://cam-ac-uk.zoom.us/j/874219
 57265\n\nA recording of this talk is available at the following link: http
 s://www.cl.cam.ac.uk/seminars/wednesday/video/\n\nThis talk is being recor
 ded. If you do not wish to be seen in the recording\, please avoid sitting
  in the front three rows of seats in the lecture theatre. Any questions as
 ked will also be included in the recording. The recording will be made ava
 ilable on the Department’s webpage
LOCATION:Lecture Theatre 1\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR