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:20240214T070246Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T094000
DTEND;TZID=Australia/Melbourne:20231214T095000
UID:siggraphasia_SIGGRAPH Asia 2023_sess124_papers_381@linklings.com
SUMMARY:AniPortraitGAN: Animatable 3D Portrait Generation from 2D Image Co
 llections
DESCRIPTION:Technical Papers, TOG\n\nYue Wu (Hong Kong University of Scien
 ce and Technology), Sicheng Xu (Microsoft Research Asia), Jianfeng Xiang (
 Tsinghua 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 h
 uman generation have primarily focused on either the human head or full bo
 dy. However, head-only videos are relatively uncommon in real life, and fu
 ll body generation typically does not deal with facial expression control 
 and still has challenges in generating high-quality results. Towards appli
 cable video avatars, we present an animatable 3D-aware GAN that generates 
 portrait images with controllable facial expression, head pose, and should
 er movements. It is a generative model trained on unstructured 2D image co
 llections without using 3D or video data. For the new task, we base our me
 thod on the generative radiance manifold representation and equip it with 
 learnable facial and head-shoulder deformations. A dual-camera rendering a
 nd adversarial learning scheme is proposed to improve the quality of the g
 enerated faces, which is critical for portrait images. A pose deformation 
 processing network is developed to generate plausible deformations for cha
 llenging regions such as long hair. Experiments show that our method, trai
 ned on unstructured 2D images, can generate diverse and high-quality 3D po
 rtraits with desired control over different properties.\n\nRegistration Ca
 tegory: Full Access\n\nSession Chair: Lin Gao (University of Chinese Acade
 my of Sciences)
URL:https://asia.siggraph.org/2023/full-program?id=papers_381&sess=sess124
END:VEVENT
END:VCALENDAR