BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Mon
 ocular Videos - Hanxue Liang\, University of Cambridge
DTSTART:20250206T140000Z
DTEND:20250206T150000Z
UID:TALK228025@talks.cam.ac.uk
CONTACT:Yancheng Cai
DESCRIPTION:Hanxue Liang will present his recent work BulletTimer. BulletT
 imer is the first motion-aware feed-forward model for real-time dynamic sc
 ene reconstruction. It takes a monocular video as input and reconstructs a
  3D Gaussian Splatting (3DGS) representation at any desired timestamp in a
  feed-forward manner within just 150 ms. This innovation opens doors for r
 eal-time interactive 3D/4D content in areas such as AR/VR\, gaming\, and v
 irtual cinematography.
LOCATION: Webinar  (via Zoom online) ID: 87457263100 Passcode: 708172
END:VEVENT
END:VCALENDAR