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:20260114T163642Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T135600
DTEND;TZID=Australia/Melbourne:20231215T141100
UID:siggraphasia_SIGGRAPH Asia 2023_sess137_papers_130@linklings.com
SUMMARY:GroomGen: A High-Quality Generative Hair Model Using Hierarchical 
 Latent Representations
DESCRIPTION:Yuxiao Zhou (ETH Zürich), Menglei Chai and Alessandro Pepe (Go
 ogle Inc.), Markus Gross (ETH Zürich), and Thabo Beeler (Google Inc.)\n\nD
 espite recent successes in hair acquisition that fits a high-dimensional h
 air model to a specific input subject, generative hair models, which estab
 lish general embedding spaces for encoding, editing, and sampling diverse 
 hairstyles, are way less explored. In this paper, we present GroomGen, the
  first generative model designed for hair geometry composed of highly-deta
 iled dense strands. Our approach is motivated by two key ideas. First, we 
 construct hair latent spaces covering both individual strands and hairstyl
 es. The latent spaces are compact, expressive, and well-constrained for hi
 gh-quality and diverse sampling. Second, we adopt a hierarchical hair repr
 esentation that parameterizes a complete hair model to three levels: singl
 e strands, sparse guide hairs, and complete dense hairs. This representati
 on is critical to the compactness of latent spaces, the robustness of trai
 ning, and the efficiency of inference. Based on this hierarchical latent r
 epresentation, our proposed pipeline consists of a strand-VAE and a hairst
 yle-VAE that encode an individual strand and a set of guide hairs to their
  respective latent spaces, a hybrid densification step that populates spar
 se guide hairs to a dense hair model, and a neural simulator that deforms 
 hair driven by head pose. GroomGen not only enables novel hairstyle sampli
 ng and plausible hairstyle interpolation, but could also enable interactiv
 e editing of complex hairstyles, or serve as strong data-driven prior for 
 hairstyle reconstruction from images. We demonstrate the superiority of ou
 r approach with qualitative examples of diverse sampled hairstyles and qua
 ntitative evaluation of generation quality regarding every single componen
 t and the entire pipeline.\n\nRegistration Category: Full Access\n\nSessio
 n Chair: Weidan Xiong (Shenzhen University, College of Computer Science an
 d Software Engineering)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_130&sess=sess137
END:VEVENT
END:VCALENDAR