BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030653Z
LOCATION:Meeting Room S221\, Level 2
DTSTART;TZID=Asia/Hong_Kong:20251216T163000
DTEND;TZID=Asia/Hong_Kong:20251216T164000
UID:siggraphasia_SIGGRAPH Asia 2025_sess131_papers_2420@linklings.com
SUMMARY:Curvature Enthusiasm: Correspondence-Free Interpolation and Matchi
 ng of Articulated 3D Shapes using Compressed Normal Cycles
DESCRIPTION:Adam Hartshorne, Allen Paul, and Tony Shardlow (University of 
 Bath) and Neill D. F. Campbell (University College London (UCL), Universit
 y of Bath)\n\nWe present an unsupervised framework for physically plausibl
 e shape interpolation and dense correspondence estimation between 3D artic
 ulated shapes. Our method uses Neural Ordinary Differential Equations to g
 enerate smooth flow fields that define diffeomorphic transformations, ensu
 ring topological consistency and preventing self-intersections while accom
 modating hard constraints, such as volume preservation. \n\nBy incorporati
 ng a lightweight skeletal structure, we impose kinematic constraints that 
 resolve symmetries without requiring manual skinning or predefined poses. 
 We enhance physical realism by interpolating skeletal motion with dual qua
 ternions and applying constrained optimization to align the flow field wit
 h the skeleton, preserving local rigidity. Additionally, we employ an effi
 cient formulation of Normal Cycles, a metric from geometric measure theory
 , to capture higher-order surface details like curvature, enabling precise
  alignment between complex articulated structures and recovery of accurate
  dense correspondence mapping.\n\nEvaluations on multiple benchmarks show 
 notable improvements over state-of-the-art methods in both interpolation q
 uality and correspondence accuracy, with consistent performance across dif
 ferent skeletal configurations, demonstrating broad applicability to shape
  matching and animation tasks.\n\nRegistration Category: Full Access, Full
  Access Supporter\n\nSession Chair: Jungdam Won (Seoul National University
 )\n\n
END:VEVENT
END:VCALENDAR