BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Learning-based Material Appearance Acquisition and Modeling for Pr
 edictive Rendering - Behnaz Kavoosighafi\, Linköpings universitet\, Sweed
 en
DTSTART:20241024T130000Z
DTEND:20241024T140000Z
UID:TALK222874@talks.cam.ac.uk
CONTACT:Rafal Mantiuk
DESCRIPTION:Recent developments in computer graphics\, and particularly wi
 thin predictive rendering\, enable highly realistic simulations of object 
 appearances. Though physically-based reflectance (PBR) models offer widesp
 read utility\, measured material reflectance data yields significantly sup
 erior accuracy through the direct empirical observation of complex light-s
 cattering interactions. Nevertheless\, acquiring and modeling reflectance 
 data causes substantial computational overhead. This work explores learnin
 g-based methods to facilitate the acquisition\, representation\, and rende
 ring of reflectance data for predictive rendering purposes. We present a c
 ompressed sensing framework to optimize gonioreflectometer-based measureme
 nts\, proposing a novel sampling strategy for surface reflectance acquisit
 ion. Furthermore\, we employ sparse representation techniques upon the exi
 sting reflectance datasets\, ensuring representational fidelity while allo
 wing for real-time rendering. This research aims to balance accuracy and e
 fficiency\, contributing to the domains of photo-realistic image synthesis
  and predictive rendering.\n\nZoom link: https://cam-ac-uk.zoom.us/j/83107
 754095?pwd=Y2ietFlkaTqqWhlZ4PUC6cSSUkJ2Vl.1
LOCATION:SS03 - William Gates Building
END:VEVENT
END:VCALENDAR