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:20250110T023312Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T093400
DTEND;TZID=Asia/Tokyo:20241206T094600
UID:siggraphasia_SIGGRAPH Asia 2024_sess139_papers_393@linklings.com
SUMMARY:Towards Unified 3D Hair Reconstruction from Single-View Portraits
DESCRIPTION:Technical Papers\n\nYujian Zheng, Yuda Qiu, and Leyang Jin (Ch
 inese University of Hong Kong, Shenzhen); Chongyang Ma, Haibin Huang, Di Z
 hang, and Pengfei Wan (Kuaishou Technology); and Xiaoguang Han (Chinese Un
 iversity of Hong Kong, Shenzhen)\n\nSingle-view 3D hair reconstruction is 
 challenging, due to the wide range of shape variations among diverse hairs
 tyles. Current state-of-the-art methods are specialized in recovering un-b
 raided 3D hairs and often take braided styles as their failure cases, beca
 use of the inherent difficulty to define priors for complex hairstyles, wh
 ether rule-based or data-based. We propose a novel strategy to enable sing
 le-view 3D reconstruction for a variety of hair types via a unified pipeli
 ne. To achieve this, we first collect a large-scale synthetic multi-view h
 air dataset SynMvHair with diverse 3D hair in both braided and un-braided 
 styles, and learn two diffusion priors specialized on hair. Then we optimi
 ze 3D Gaussian-based hair from the priors with two specially designed modu
 les, i.e. view-wise and pixel-wise Gaussian refinement. Our experiments de
 monstrate that reconstructing braided and un-braided 3D hair from single-v
 iew images via a unified approach is possible and our method achieves the 
 state-of-the-art performance in recovering complex hairstyles. It is worth
  to mention that our method shows good generalization ability to real imag
 es, although it learns hair priors from synthetic data. Code and data are 
 available at https://unihair24.github.io\n\nRegistration Category: Full Ac
 cess, Full Access Supporter\n\nLanguage Format: English Language\n\nSessio
 n Chair: Kui Wu (LightSpeed Studios)
URL:https://asia.siggraph.org/2024/program/?id=papers_393&sess=sess139
END:VEVENT
END:VCALENDAR