BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Perceptual quality metric and loss function for 3D and temporal co
 nsistency - Fei Yin\, University of Cambridge
DTSTART:20250529T130000Z
DTEND:20250529T140000Z
UID:TALK232789@talks.cam.ac.uk
CONTACT:Yancheng Cai
DESCRIPTION:To better train and evaluate 3D reconstruction methods (NeRF\,
  Gaussian Splatting) or 3D generative models\, both for static (3D) and dy
 namic (4D) scenes\, we will develop a new full-reference quality metric an
 d no-reference loss function. Those will be trained and validated on a new
  4D quality dataset\, with the subjective quality measured in stereoscopic
  presentation (e.g.\, on a VR headset). The developed techniques will impr
 ove 3D and temporal consistency of the rendered views\, resulting in fewer
  temporal artefacts. They will also allow automatic hyper-parameter tuning
  and more reliable evaluation and comparison of 3D rendering techniques.
LOCATION:SS03 - William Gates Building
END:VEVENT
END:VCALENDAR