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:20260817T171534Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T132300
DTEND;TZID=Asia/Tokyo:20241205T133400
UID:siggraphasia_SIGGRAPH Asia 2024_sess130_papers_509@linklings.com
SUMMARY:Controllable Shape Modeling with Neural Generalized Cylinder
DESCRIPTION:Xiangyu Zhu (Chinese University of Hong Kong, Shenzhen); Zhiqi
 n Chen (Adobe Research); Ruizhen Hu (Shenzhen University (SZU)); and Xiaog
 uang Han (Chinese University of Hong Kong, Shenzhen)\n\nNeural shape repre
 sentation, such as neural signed distance field (NSDF), becomes more and m
 ore popular in shape modeling as its ability to deal with complex topology
  and arbitrary resolution. Due to the implicit manner to use features for 
 shape representation, manipulating the shapes faces inherent challenge of 
 inconvenience, since the feature cannot be intuitively edited. In this wor
 k, we propose neural generalized cylinder (NGC) for explicit manipulation 
 of NSDF, which is an extension of traditional generalized cylinder (GC). S
 pecifically, we define a central curve first and assign neural features al
 ong the curve to represent the profiles. Then NSDF is defined on the relat
 ive coordinates of a specialized GC with oval-shaped profiles. By using th
 e relative coordinates, NSDF can be explicitly controlled via manipulation
  of the GC. To this end, we apply NGCto many non-rigid deformation tasks l
 ike complex curved deformation, local scaling and twisting for shapes. The
  comparison on shape deformation with other methods proves the effectivene
 ss and efficiency of NGC. Furthermore, NGC could utilize the neural featur
 e for shape blending by a simple neural feature interpolation.\n\nRegistra
 tion Category: Full Access, Full Access Supporter\n\nLanguage Format: Engl
 ish Language\n\nSession Chair: Noam Aigerman (University of Montreal, Mila
 )\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_509&sess=sess130
END:VEVENT
END:VCALENDAR