BEGIN:VCALENDAR VERSION:2.0 PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92// CALSCALE:GREGORIAN METHOD:PUBLISH UID:36373463-6639-4436-b363-313037663034 X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde X-WR-TIMEZONE:America/Vancouver X-WR-CALNAME:Domes to Drones: Self-Supervised Active Triangulation for 3D H uman Pose Reconstruction - Cristian Sminchisescu\, Professor\, Lund Univer sity / Google Zurich BEGIN:VTIMEZONE TZID:America/Vancouver TZUNTIL:20211107T090000Z BEGIN:STANDARD TZNAME:PST DTSTART:20191103T020000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RDATE:20201101T020000 END:STANDARD BEGIN:DAYLIGHT TZNAME:PDT DTSTART:20190310T020000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RDATE:20200308T020000 RDATE:20210314T020000 END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT UID:af0bec14-73b5-4938-b703-13fd7a9ab4e9 DTSTAMP:20260308T154327Z CLASS:PUBLIC CREATED:20191127T232336Z DESCRIPTION:Abstract: Existing state-of-the-art estimation systems can dete ct 2d poses of multiple people in images quite reliably. In contrast\, 3d pose estimation from a single image is ill-posed due to occlusion and dept h ambiguities. Assuming access to multiple cameras\, or given an active sy stem able to position itself to observe the scene from multiple viewpoints \, reconstructing 3d pose from 2d measurements becomes well-posed within t he framework of standard multi-view geometry. Less clear is what is an inf ormative set of viewpoints for accurate 3d reconstruction\, particularly i n complex scenes\, where… DTSTART;TZID=America/Vancouver:20191209T100000 DTEND;TZID=America/Vancouver:20191209T110000 LAST-MODIFIED:20210611T171034Z LOCATION:ICCS - X836\, ICICS Computer Science\, 2366 Main Mall\, Vancouver\ , BC SUMMARY:Domes to Drones: Self-Supervised Active Triangulation for 3D Human Pose Reconstruction - Cristian Sminchisescu\, Professor\, Lund University / Google Zurich TRANSP:OPAQUE URL:https://caida.ubc.ca/event/domes-drones-self-supervised-active-triangul ation-3d-human-pose-reconstruction-cristian END:VEVENT END:VCALENDAR