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:20260805T205602Z
LOCATION:Room 408 B
DTSTART;TZID=America/Los_Angeles:20260722T112500
DTEND;TZID=America/Los_Angeles:20260722T113500
UID:siggraph_SIGGRAPH 2026_sess153_papers_823@linklings.com
SUMMARY:MegaNorm: Local Patches Embedding for Efficient and Robust Point N
 ormal Orientation at Super-Large Scale
DESCRIPTION:Zhuodong Li, Zengke Liu, Fei Hou, Xuhui Chen, and Wencheng Wan
 g (Institute of Software, Chinese Academy of Sciences; University of Chine
 se Academy of Sciences) and Ying He (Nanyang Technological University)\n\n
 MegaNorm is a fast, accurate, and robust method for orienting normals in n
 on-watertight, scene-scale point clouds, scaling to ~50M points in under 1
 0 minutes. It uses two feed-forward networks: one orients local patches in
  parallel, while a lightweight MLP evaluates pairwise consistency. Finally
 , a 0–1 integer program enforces global consistency.\n\nInterest Area: Res
 earch & Education\n\nKeyword: Artificial Intelligence/Machine Learning, Ge
 nerative AI, Geometry, Modeling, Rendering, Simulation\n\nRegistration Cat
 egory: Full Conference Supporter, Full Conference\n\nSession Chair: Oded S
 tein (Technion, University of Southern California)\n\n
END:VEVENT
END:VCALENDAR