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 B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T151300
DTEND;TZID=Asia/Tokyo:20241205T152700
UID:siggraphasia_SIGGRAPH Asia 2024_sess133_papers_1032@linklings.com
SUMMARY:Robust Symmetry Detection via Riemannian Langevin Dynamics
DESCRIPTION:Technical Papers\n\nJihyeon Je, Jiayi Liu, Guandao Yang, Boyan
 g Deng, Shengqu Cai, and Gordon Wetzstein (Stanford University); Or Litany
  (Technion); and Leonidas Guibas (Stanford University)\n\nSymmetries are u
 biquitous across all kinds of objects, whether in nature or in man-made cr
 eations. While these symmetries may seem intuitive to the human eye, detec
 ting them with a machine is nontrivial due to the vast search space. Class
 ical geometry-based methods work by aggregating "votes" for each symmetry 
 but struggle with noise. In contrast, learning-based methods may be more r
 obust to noise, but often overlook partial symmetries due to the scarcity 
 of annotated data. In this work, we address this challenge by proposing a 
 novel symmetry detection method that marries classical symmetry detection 
 techniques with recent advances in generative modeling. Specifically, we a
 pply Langevin dynamics to a redefined symmetry space to enhance robustness
  against noise. We provide empirical results on a variety of shapes that s
 uggest our method is not only robust to noise, but can also identify both 
 partial and global symmetries. Moreover, we demonstrate the utility of our
  detected symmetries in various downstream tasks, such as compression and 
 symmetrization of noisy shapes.\n\nRegistration Category: Full Access, Ful
 l Access Supporter\n\nLanguage Format: English Language\n\nSession Chair: 
 Mirela Ben-Chen (Technion – Israel Institute of Technology)
URL:https://asia.siggraph.org/2024/program/?id=papers_1032&sess=sess133
END:VEVENT
END:VCALENDAR