BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260417T190156Z
LOCATION:West Building\, Rooms 211-214
DTSTART;TZID=America/Los_Angeles:20250813T091000
DTEND;TZID=America/Los_Angeles:20250813T092000
UID:siggraph_SIGGRAPH 2025_sess128_papers_921@linklings.com
SUMMARY:PDT: Point Distribution Transformation with Diffusion Models
DESCRIPTION:Jionghao Wang (Texas A&M University); Cheng Lin (University of
  Hong Kong); Yuan Liu (HKUST); Rui Xu and Zhiyang Dou (University of Hong 
 Kong); Xiaoxiao Long (Nanjing University); Haoxiang Guo (Skywork AI, Kunlu
 n Inc.); Taku Komura (University of Hong Kong); and Xin Li and Wenping Wan
 g (Texas A&M University)\n\nPDT is a novel framework that uses diffusion m
 odels to transform unstructured point clouds into semantically meaningful 
 and structured distributions, such as keypoints, joints, and feature lines
 . Exploring complex point distribution transformation, PDT captures fine-g
 rained geometry and semantics, offering a versatile tool for diverse tasks
 .\n\nInterest Area: Research & Education\n\nRecording: Livestreamed, Not L
 ivestreamed, Recorded, Not Recorded\n\nRegistration Category: Full Confere
 nce, Virtual Access, Wednesday\n\nSession Chair: Yael Vinker (Massachusett
 s Institute of Technology (MIT), MIT CSAIL)\n\n
END:VEVENT
END:VCALENDAR