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:20260817T171531Z
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:Stevo Racković (University of Lisbon), Dušan Jakovetić (Univer
 sity of Novi Sad), and Cláudia Soares (NOVA School of Science and Technolo
 gy)\n\nIn this paper, we present an advanced approach to solving the inver
 se rig problem in blendshape animation, using high-quality corrective blen
 dshapes. Our algorithm introduces novel enhancements in three key areas: e
 nsuring high data fidelity in reconstructed meshes, achieving greater spar
 sity in weight distributions, and facilitating smoother frame-to-frame tra
 nsitions. While the incorporation of corrective terms is a known practice,
  our method differentiates itself by employing a unique combination of $l_
 1$ norm regularization for sparsity and a temporal smoothness constraint t
 hrough roughness penalty, focusing on the sum of second differences in con
 secutive frame weights.\nA significant innovation in our approach is the t
 emporal decoupling of blendshapes, which permits simultaneous optimization
  across entire animation sequences. This feature sets our work apart from 
 existing methods and contributes to a more efficient and effective solutio
 n. Our algorithm exhibits a marked improvement in maintaining data fidelit
 y and ensuring smooth frame transitions when compared to prior approaches 
 that either lack smoothness regularization or rely solely on linear blends
 hape models. In addition to superior mesh resemblance and smoothness, our 
 method offers practical benefits, including reduced computational complexi
 ty and execution time, achieved through a novel parallelization strategy u
 sing clustering methods.\nOur results not only advance the state-of-the-ar
 t in terms of fidelity, sparsity, and smoothness in inverse rigging but al
 so introduce significant efficiency improvements. The source code will be 
 made available upon acceptance of the paper.\n\nRegistration Category: Ful
 l Access, Full Access Supporter\n\nLanguage Format: English Language\n\nSe
 ssion Chair: Jungdam Won (Seoul National University)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_917&sess=sess117
END:VEVENT
END:VCALENDAR