BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240214T070241Z
LOCATION:Darling Harbour Theatre\, Level 2 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T093000
DTEND;TZID=Australia/Melbourne:20231212T124500
UID:siggraphasia_SIGGRAPH Asia 2023_sess209_papers_401@linklings.com
SUMMARY:HyperDreamer: Hyper-Realistic 3D Content Generation and Editing fr
 om a Single Image
DESCRIPTION:Technical Papers\n\nTong Wu and Zhibing Li (The Chinese Univer
 sity of Hong Kong, Shanghai AI Laboratory); Shuai Yang (Shanghai Jiao Tong
  University, Shanghai AI Laboratory); Pan Zhang (Shanghai AI Laboratory); 
 Xingang Pan (Max Planck Institute for Informatics); Jiaqi Wang (Shanghai A
 I Laboratory); Dahua Lin (The Chinese University of Hong Kong, Shanghai AI
  Laboratory); and Ziwei Liu (Nanyang Technological University)\n\n3D conte
 nt creation from a single image is a long-standing yet highly desirable ta
 sk. Recent advances introduce 2D diffusion priors, yielding reasonable res
 ults. However, existing methods are not hyper-realistic enough for post-ge
 neration usage, as users cannot view, render and edit the resulting 3D con
 tent from a full range. To address these challenges, we introduce Hyper-Dr
 eamer with several key designs and appealing properties: 1) Full-range vie
 wable: 360◦ mesh modeling with high-resolution textures enables the creati
 on of visually compelling 3D models from a full range of observation point
 s. 2) Full-range renderable: Fine-grained semantic segmentation and data-d
 riven priors are incorporated as guidance to learn reasonable albedo, roug
 hness, and specular properties of the materials, enabling semantic-aware a
 rbitrary material estimation. 3) Full-range editable: For a generated mode
 l or their own data, users can interactively select any region via a few c
 licks and efficiently edit the texture with text-based guidance. Extensive
  experiments demonstrate the effectiveness of HyperDreamer in modeling reg
 ion-aware materials with high-resolution textures and enabling user-friend
 ly editing. We believe that HyperDreamer holds promise for adVancing 3D co
 ntent creation and finding applications in various domains.\n\nRegistratio
 n Category: Full Access, Enhanced Access, Trade Exhibitor, Experience Hall
  Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=papers_401&sess=sess209
END:VEVENT
END:VCALENDAR