BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Modeling Light for View Synthesis - Dr. Ben Mildenhall (Google Res
 earch)
DTSTART:20220826T100000Z
DTEND:20220826T110000Z
UID:TALK177899@talks.cam.ac.uk
CONTACT:Gwangbin Bae
DESCRIPTION:*Abstract*\n\nRecent years have seen an immense amount of prog
 ress in many-input view synthesis in particular\, largely driven by the us
 e of volumetric scene representations in an inverse rendering framework. H
 owever\, when it comes to taking a careful\, scientific approach to radiom
 etry and image formation\, these methods are still relatively immature. In
  this talk\, I will address multiple aspects of "modeling" in view synthes
 is: how we model outgoing radiance in 3D scene representations\, and how w
 e model image formation inside the camera. I will also discuss dataset cap
 ture\, give some thoughts on the current state of neural volumetric scene 
 representations\, and show some cool results.\n\n*Bio*\n\nBen is a researc
 h scientist at Google Research\, where he works on problems in computer vi
 sion and graphics. He recently received his PhD from UC Berkeley\, where h
 e was advised by Ren Ng and supported by a Hertz fellowship. In the summer
  of 2017\, he was an intern in Marc Levoy's group in Google Research. In t
 he summer of 2018\, he worked with Rodrigo Ortiz-Cayon and Abhishek Kar at
  Fyusion. He did his undergrad at Stanford University and worked at Pixar 
 Research in the summer of 2014.\n\n*Location*\n\nThe talk will be given at
  *Lecture Theatre 1 (LT1)* in the Engineering Department (Trumpington St\,
  Cambridge CB2 1PZ).\n\n*Google Calendar*\n\nTo get updates on future semi
 nars\, please subscribe to the following Google calendar:\nhttps://calenda
 r.google.com/calendar/u/0?cid=c2pjcHN0YXM2N3QyMWU3c2FqNjBqNWNiYXNAZ3JvdXAu
 Y2FsZW5kYXIuZ29vZ2xlLmNvbQ\n
LOCATION:Lecture Theatre 1 (LT1)\, Engineering Department\, Trumpington St
 \, Cambridge (CB2 1PZ)
END:VEVENT
END:VCALENDAR