BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Hypernetwork approach to generating 3D objects - Dr hab. Przemysla
 w Spurek\, Jagiellonian University in Kraków
DTSTART:20230314T120000Z
DTEND:20230314T130000Z
UID:TALK197932@talks.cam.ac.uk
CONTACT:Slawomir Tadeja
DESCRIPTION:Abstract:\nRecently\, generative models for 3D objects are gai
 ning much popularity in virtual (VR) and augmented reality (AR) applicatio
 ns. Training such models using standard 3D representations\, like voxels o
 r point clouds\, is challenging and requires complex tools for proper colo
 ur rendering. In order to overcome this limitation\, Neural Radiance Field
 s (NeRFs) offer a state-of-the-art quality in synthesizing novel views of 
 complex 3D scenes from a small subset of 2D images.\n\nIn the presentation
 \, I describe generative models which use hypernetworks paradigm to produc
 e 3D objects represented by NeRF. The advantage of the models over existin
 g approaches is that it produces a dedicated NeRF representation for the o
 bject without sharing some global parameters of the rendering component.\n
 \nBio:\nDr Hab. Przemyslaw Spurek received a master's degree in mathematic
 s and a PhD in computer science from the Jagiellonian University\, Krakow\
 , Poland\, in 2009 and 2014\, respectively. He is currently an Assistant P
 rofessor at the Institute of Computer Science\, Jagiellonian University. H
 e co-authored several research papers published in well-known journals and
  presented at the top Machine Learning conferences\, including NeurIPS\, I
 CML\, AISTATS\, and IROS. His research interests include deep learning\, e
 specially generative models\, and meta-learning.
LOCATION:Institute of Manufacturing (IfM)\, Seminar Room 2
END:VEVENT
END:VCALENDAR