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:20240214T070240Z
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_381@linklings.com
SUMMARY:AniPortraitGAN: Animatable 3D Portrait Generation from 2D Image Co
 llections
DESCRIPTION:Technical Papers\n\nYue Wu (Hong Kong University of Science an
 d Technology), Sicheng Xu (Microsoft Research Asia), Jianfeng Xiang (Tsing
 hua University), Fangyun Wei (Microsoft Research Asia), Qifeng Chen (Hong 
 Kong University of Science and Technology), and Jiaolong Yang and Xin Tong
  (Microsoft Research Asia)\n\nPrevious animatable 3D-aware GANs for human 
 generation have primarily focused on either the human head or full body. H
 owever, head-only videos are relatively uncommon in real life, and full bo
 dy generation typically does not deal with facial expression control and s
 till has challenges in generating high-quality results. Towards applicable
  video avatars, we present an animatable 3D-aware GAN that generates portr
 ait images with controllable facial expression, head pose, and shoulder mo
 vements. It is a generative model trained on unstructured 2D image collect
 ions without using 3D or video data. For the new task, we base our method 
 on the generative radiance manifold representation and equip it with learn
 able facial and head-shoulder deformations. A dual-camera rendering and ad
 versarial learning scheme is proposed to improve the quality of the genera
 ted faces, which is critical for portrait images. A pose deformation proce
 ssing network is developed to generate plausible deformations for challeng
 ing regions such as long hair. Experiments show that our method, trained o
 n unstructured 2D images, can generate diverse and high-quality 3D portrai
 ts with desired control over different properties.\n\nRegistration Categor
 y: Full Access, Enhanced Access, Trade Exhibitor, Experience Hall Exhibito
 r
URL:https://asia.siggraph.org/2023/full-program?id=papers_381&sess=sess209
END:VEVENT
END:VCALENDAR