BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T171538Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241204T131100
DTEND;TZID=Asia/Tokyo:20241204T132300
UID:siggraphasia_SIGGRAPH Asia 2024_sess117_papers_277@linklings.com
SUMMARY:High-quality Animatable Eyelid Shapes from Lightweight Captures
DESCRIPTION:Junfeng Lyu and Feng Xu (Tsinghua University, China)\n\nHigh-q
 uality eyelid reconstruction and animation are challenging for the subtle 
 details and complicated deformations. Previous works usually suffer from t
 he trade-off between the capture costs and the quality of details. In this
  paper, we propose a novel method that can achieve detailed eyelid reconst
 ruction and animation by only using an RGB video captured by a mobile phon
 e. Our method utilizes both static and dynamic information of eyeballs (e.
 g., positions and rotations) to assist the eyelid reconstruction, cooperat
 ing with an automatic eyeball calibration method to get the required eyeba
 ll parameters. Furthermore, we develop a neural eyelid control module to a
 chieve the semantic animation control of eyelids. To the best of our knowl
 edge, we present the first method for high-quality eyelid reconstruction a
 nd animation from lightweight captures. Extensive experiments on both synt
 hetic and real data show that our method can provide more detailed and rea
 listic results compared with previous methods based on the same-level capt
 ure setups. The code is available at https://github.com/StoryMY/AniEyelid.
 \n\nRegistration Category: Full Access, Full Access Supporter\n\nLanguage 
 Format: English Language\n\nSession Chair: Jungdam Won (Seoul National Uni
 versity)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_277&sess=sess117
END:VEVENT
END:VCALENDAR