BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250110T023313Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T154100
DTEND;TZID=Asia/Tokyo:20241206T155500
UID:siggraphasia_SIGGRAPH Asia 2024_sess148_papers_437@linklings.com
SUMMARY:iSeg: Interactive 3D Segmentation via Interactive Attention
DESCRIPTION:Technical Papers\n\nItai Lang, Fei Xu, and Dale Decatur (Unive
 rsity of Chicago); Sudarshan Babu (Toyota Technological Institute at Chica
 go (TTIC)); and Rana Hanocka (University of Chicago)\n\nWe present iSeg, a
  new interactive technique for segmenting 3D shapes. Previous works have f
 ocused mainly on leveraging pre-trained 2D foundation models for 3D segmen
 tation based on text. However, text may be insufficient for accurately des
 cribing fine-grained spatial segmentations. Moreover, achieving a consiste
 nt 3D segmentation using a 2D model is challenging since occluded areas of
  the same semantic region may not be visible together from any 2D view. Th
 us, we design a segmentation method conditioned on fine user clicks, which
  operates entirely in 3D. Our system accepts user clicks directly on the s
 hape's surface, indicating the inclusion or exclusion of regions from the 
 desired shape partition. To accommodate various click settings, we propose
  a novel interactive attention module capable of processing different numb
 ers and types of clicks, enabling the training of a single unified interac
 tive segmentation model. We apply iSeg to a myriad of shapes from differen
 t domains, demonstrating its versatility and faithfulness to the user's sp
 ecifications.\n\nRegistration Category: Full Access, Full Access Supporter
 \n\nLanguage Format: English Language\n\nSession Chair: Peng Song (Singapo
 re University of Technology and Design (SUTD))
URL:https://asia.siggraph.org/2024/program/?id=papers_437&sess=sess148
END:VEVENT
END:VCALENDAR
