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:20260817T171536Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T090000
DTEND;TZID=Asia/Tokyo:20241206T101000
UID:siggraphasia_SIGGRAPH Asia 2024_sess139@linklings.com
SUMMARY:Beauty Salon: Hair, Face, Lips, and Teeth
DESCRIPTION:Each Paper gives a 10 minute presentation.\n\nCurly-Cue: Geome
 tric Methods for Highly Coiled Hair\n\nWe present geometric methods for ge
 nerating shapes that are characteristic of highly coiled hair. Different f
 eatures become visually relevant when hairs are well-approximated by high-
 frequency helices instead of a low-frequency curves, so we present algorit
 hms for three such phenomena. First, a Four...\n\n\nHaomiao Wu and Alvin S
 hi (Yale University), A.M. Darke (University of California Santa Cruz), an
 d Theodore Kim (Yale University)\n---------------------\nSPARK: Self-super
 vised Personalized Real-time Monocular Face Capture\n\nFeedforward monocul
 ar face capture methods seek to reconstruct posed faces from a single imag
 e of a person. Current state of the art approaches have the ability to reg
 ress parametric 3D face models in real-time across a wide range of identit
 ies, lighting conditions and poses by leveraging large imag...\n\n\nKelian
  Baert (Technicolor Group, Institut national de recherche en informatique 
 et en automatique (INRIA) Rennes); Shrisha Bharadwaj (Max Planck Institute
  for Intelligent Systems); Fabien Castan and Benoit Maujean (Technicolor G
 roup); Marc Christie (Institut national de recherche en informatique et en
  automatique (INRIA)); Victoria Fernández Abrevaya (Max Planck Institute f
 or Intelligent Systems); and Adnane Boukhayma (Institut national de recher
 che en informatique et en automatique (INRIA))\n---------------------\nGro
 omCap: High-Fidelity Prior-Free Hair Capture\n\nDespite recent advances in
  multi-view hair reconstruction, achieving strand-level precision remains 
 a significant challenge due to inherent limitations in existing capture pi
 pelines. We introduce GroomCap, a novel multi-view hair capture method tha
 t reconstructs faithful and high-fidelity hair geome...\n\n\nYuxiao Zhou (
 ETH Zürich); Menglei Chai, Daoye Wang, Sebastian Winberg, Erroll Wood, and
  Kripasindhu Sarkar (Google Inc.); Markus Gross (ETH Zürich); and Thabo Be
 eler (Google Inc.)\n---------------------\nTowards Unified 3D Hair Reconst
 ruction from Single-View Portraits\n\nSingle-view 3D hair reconstruction i
 s challenging, due to the wide range of shape variations among diverse hai
 rstyles. Current state-of-the-art methods are specialized in recovering un
 -braided 3D hairs and often take braided styles as their failure cases, be
 cause of the inherent difficulty to define...\n\n\nYujian Zheng, Yuda Qiu,
  and Leyang Jin (Chinese University of Hong Kong, Shenzhen); Chongyang Ma,
  Haibin Huang, Di Zhang, and Pengfei Wan (Kuaishou Technology); and Xiaogu
 ang Han (Chinese University of Hong Kong, Shenzhen)\n---------------------
 \nThe Lips, the Teeth, the tip of the Tongue: LTT Tracking\n\nA mesh-based
  generative model of the inner-mouth system is presented, which includes t
 eeth and gums for the upper and lower jaw, the tongue, and their placement
  inside the human head. The model is capable of capturing person-specific 
 detail, enabling the creation of highly accurate avatars that exce...\n\n\
 nFeisal Rasras, Stanislav Pidhorskyi, and Tomas Simon (Reality Labs Resear
 ch); Hallison Paz (Instituto Nacional de Matemática Pura e Aplicada (IMPA)
 ); and He Wen, Jason Saragih, and Javier Romero (Reality Labs Research)\n-
 --------------------\nHairmony: Fairness-aware hairstyle classification\n\
 nWe present a method for prediction of a person's hairstyle from a single 
 image. Despite growing use cases in user digitization and enrollment for v
 irtual experiences, available methods are limited, particularly in the ran
 ge of hairstyles they can capture. Human hair is extremely diverse and lac
 ks an...\n\n\nGivi Meishvili, James Clemoes, Charlie Hewitt, Zafiirah Hose
 nie, Xian Xiao, Martin de La Gorce, Tibor Takacs, Tadas Baltrusaitis, Anto
 nio Criminisi, and Chyna McRae (Microsoft); Nina Jablonski (Pennsylvania S
 tate University); and Marta Wilczkowiak (Microsoft)\n\nRegistration Catego
 ry: Full Access, Full Access Supporter\n\nLanguage Format: English Languag
 e\n\nSession Chair: Kui Wu (LIGHTSPEED)
END:VEVENT
END:VCALENDAR