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 B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241204T135800
DTEND;TZID=Asia/Tokyo:20241204T140900
UID:siggraphasia_SIGGRAPH Asia 2024_sess117_papers_917@linklings.com
SUMMARY:Refined Inverse Rigging: A Balanced Approach to High-fidelity Blen
 dshape Animation
DESCRIPTION:Technical Papers\n\nStevo Racković (University of Lisbon), Duš
 an Jakovetić (University of Novi Sad), and Cláudia Soares (NOVA School of 
 Science and Technology)\n\nIn this paper, we present an advanced approach 
 to solving the inverse rig problem in blendshape animation, using high-qua
 lity corrective blendshapes. Our algorithm introduces novel enhancements i
 n three key areas: ensuring high data fidelity in reconstructed meshes, ac
 hieving greater sparsity in weight distributions, and facilitating smoothe
 r frame-to-frame transitions. While the incorporation of corrective terms 
 is a known practice, our method differentiates itself by employing a uniqu
 e combination of $l_1$ norm regularization for sparsity and a temporal smo
 othness constraint through roughness penalty, focusing on the sum of secon
 d differences in consecutive frame weights.\nA significant innovation in o
 ur approach is the temporal decoupling of blendshapes, which permits simul
 taneous optimization across entire animation sequences. This feature sets 
 our work apart from existing methods and contributes to a more efficient a
 nd effective solution. Our algorithm exhibits a marked improvement in main
 taining data fidelity and ensuring smooth frame transitions when compared 
 to prior approaches that either lack smoothness regularization or rely sol
 ely on linear blendshape models. In addition to superior mesh resemblance 
 and smoothness, our method offers practical benefits, including reduced co
 mputational complexity and execution time, achieved through a novel parall
 elization strategy using clustering methods.\nOur results not only advance
  the state-of-the-art in terms of fidelity, sparsity, and smoothness in in
 verse rigging but also introduce significant efficiency improvements. The 
 source code will be made available upon acceptance of the paper.\n\nRegist
 ration Category: Full Access, Full Access Supporter\n\nLanguage Format: En
 glish Language\n\nSession Chair: Jungdam Won (Seoul National University)
URL:https://asia.siggraph.org/2024/program/?id=papers_917&sess=sess117
END:VEVENT
END:VCALENDAR