BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:62323131-6564-4631-b034-386137643362
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Learning Generative Models of 3D Shapes: From Implicit Functio
 ns to Structured Representations - Richard (Hao) Zhang\, Professor\, SFU
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20221106T090000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20201101T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20211107T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20200308T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20210314T020000
RDATE:20220313T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:8521f720-eb75-48ff-856e-cf1e57344258
DTSTAMP:20260415T060136Z
CLASS:PUBLIC
CREATED:20210127T231719Z
DESCRIPTION:Please register for this event here. Abstract: Unlike images an
 d video\, 3D shapes are not confined to one standard representation. This 
 is one of the challenges we face when developing deep neural networks (DNN
 s) to learn generative models of 3D shapes or virtual scenes. So far\, vox
 el grids\, multi-view images\, point clouds\, and integrated surface patch
 es have all been considered. In this talk\, I show that traditional convol
 utional neural networks operating on pixels/voxels may not be best suited 
 for the task. I first present IM-Net\, our recent work on learning implici
 t functions\, and show the…
DTSTART;TZID=America/Vancouver:20210222T130000
DTEND;TZID=America/Vancouver:20210222T140000
LAST-MODIFIED:20210324T232202Z
LOCATION:Please register to receive the Zoom link
SUMMARY:Learning Generative Models of 3D Shapes: From Implicit Functions to
  Structured Representations - Richard (Hao) Zhang\, Professor\, SFU
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/learning-generative-models-3d-shapes-implici
 t-functions-structured-representations-richard
END:VEVENT
END:VCALENDAR