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_321@linklings.com
SUMMARY:Learning to Generate 3D Shapes from a Single Example
DESCRIPTION:Technical Papers\n\nLearning to Generate 3D Shapes from a Sing
 le Example\n\nWu, Zheng\n\nExisting generative models for 3D shapes are ty
 pically trained on a large 3D dataset, often of a specific object category
 .  In this paper, we investigate the deep generative model that learns fro
 m only a single reference 3D shape. Specifically, we present a multi-scale
  GAN-based model designed to capture the input shape's geometric features 
 across a range of spatial scales. To avoid large memory and computational 
 cost induced by operating on the 3D volume, we build our generator atop th
 e tri-plane hybrid representation, which requires only 2D convolutions.  W
 e train our generative model on a voxel pyramid of the reference shape, wi
 thout the need of any external supervision or manual annotation.  Once tra
 ined, our model can generate diverse and high-quality 3D shapes possibly o
 f different sizes and aspect ratios. The resulting shapes present variatio
 ns across different scales, and at the same time retain the global structu
 re of the reference shape. Through extensive evaluation, both qualitative 
 and quantitative, we demonstrate that our model can generate 3D shapes of 
 various types.\n\nRegistration Category: FULL ACCESS, EXPERIENCE PLUS ACCE
 SS, EXPERIENCE ACCESS, TRADE EXHIBITOR\n\nLanguage: ENGLISH\n\nFormat: IN-
 PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_321&sess=sess15
 3
END:VEVENT
END:VCALENDAR