BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030656Z
LOCATION:Meeting Room S426+S427\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251217T090000
DTEND;TZID=Asia/Hong_Kong:20251217T091000
UID:siggraphasia_SIGGRAPH Asia 2025_sess134_papers_1299@linklings.com
SUMMARY:Auto Hair Card Extraction for Smooth Hair with Differentiable Rend
 ering
DESCRIPTION:Zhongtian Zheng, Tao Huang, Haozhe Su, Xueqi Ma, Yuefan Shen, 
 and Tongtong Wang (LIGHTSPEED); Yin Yang (University of Utah); and Xifeng 
 Gao, Zherong Pan, and Kui Wu (LIGHTSPEED)\n\nHair cards remain a widely us
 ed representation for hair modeling in real-time applications, offering a 
 practical trade-off between visual fidelity, memory usage, and performance
 . However, generating high-quality hair card models remains a challenging 
 and labor-intensive task. This work presents an automated pipeline for con
 verting strand-based hair models into hair card models with a limited numb
 er of cards and textures while preserving the hairstyle appearance.  Our k
 ey idea is a novel differentiable representation where each strand is enco
 ded as a projected 2D spline in the texture space, which enables efficient
  optimization with differentiable rendering and structured results respect
 ing the hair geometry.  Our method is evaluated on a wide range of hairsty
 les, including straight, wavy, curly, and coily hairs.\n\nRegistration Cat
 egory: Full Access, Full Access Supporter\n\nSession Chair: Menglei Chai (
 Google)\n\n
END:VEVENT
END:VCALENDAR