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:20260114T163644Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T094000
DTEND;TZID=Australia/Melbourne:20231214T095000
UID:siggraphasia_SIGGRAPH Asia 2023_sess148_papers_401@linklings.com
SUMMARY:HyperDreamer: Hyper-Realistic 3D Content Generation and Editing fr
 om a Single Image
DESCRIPTION:Tong Wu and Zhibing Li (The Chinese University of Hong Kong, S
 hanghai AI Laboratory); Shuai Yang (Shanghai Jiao Tong University, Shangha
 i AI Laboratory); Pan Zhang (Shanghai AI Laboratory); Xingang Pan (Max Pla
 nck Institute for Informatics); Jiaqi Wang (Shanghai AI Laboratory); Dahua
  Lin (The Chinese University of Hong Kong, Shanghai AI Laboratory); and Zi
 wei Liu (Nanyang Technological University)\n\n3D content creation from a s
 ingle image is a long-standing yet highly desirable task. Recent advances 
 introduce 2D diffusion priors, yielding reasonable results. However, exist
 ing methods are not hyper-realistic enough for post-generation usage, as u
 sers cannot view, render and edit the resulting 3D content from a full ran
 ge. To address these challenges, we introduce Hyper-Dreamer with several k
 ey designs and appealing properties: 1) Full-range viewable: 360◦ mesh mod
 eling with high-resolution textures enables the creation of visually compe
 lling 3D models from a full range of observation points. 2) Full-range ren
 derable: Fine-grained semantic segmentation and data-driven priors are inc
 orporated as guidance to learn reasonable albedo, roughness, and specular 
 properties of the materials, enabling semantic-aware arbitrary material es
 timation. 3) Full-range editable: For a generated model or their own data,
  users can interactively select any region via a few clicks and efficientl
 y edit the texture with text-based guidance. Extensive experiments demonst
 rate the effectiveness of HyperDreamer in modeling region-aware materials 
 with high-resolution textures and enabling user-friendly editing. We belie
 ve that HyperDreamer holds promise for adVancing 3D content creation and f
 inding applications in various domains.\n\nRegistration Category: Full Acc
 ess\n\nSession Chair: Lin Lu (Shandong University)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_401&sess=sess148
END:VEVENT
END:VCALENDAR