BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035307Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_167@linklings.com
SUMMARY:SHRED: 3D Shape Region Decomposition with Learned Local Operations
DESCRIPTION:Technical Papers\n\nSHRED: 3D Shape Region Decomposition with 
 Learned Local Operations\n\nJones, Habib, Ritchie\n\nWe present SHRED, a m
 ethod for 3D SHape REgion Decomposition. SHRED takes a 3D point cloud as i
 nput and uses learned local operations to produce a segmentation that appr
 oximates fine-grained part instances. We endow SHRED with three decomposit
 ion operations: splitting regions, fixing the boundaries between regions, 
 and merging regions together. Modules are trained independently and locall
 y, allowing SHRED to generate high-quality segmentations for categories no
 t seen during training. We train and evaluate SHRED with fine-grained segm
 entations from PartNet; using its merge-threshold hyperparameter, we show 
 that SHRED produces segmentations that better respect ground-truth annotat
 ions compared with baseline methods, at any desired decomposition granular
 ity. Finally, we demonstrate that SHRED is useful for downstream applicati
 ons, out-performing all baselines on zero-shot fine-grained part instance 
 segmentation and few-shot fine-grained semantic segmentation when combined
  with methods that learn to label shape regions.\n\nRegistration Category:
  FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE ACCESS, TRADE EXHIBITOR\n
 \nLanguage: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_167&sess=sess15
 3
END:VEVENT
END:VCALENDAR