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:20260817T171530Z
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:Jihyeon Je, Jiayi Liu, Guandao Yang, Boyang Deng, Shengqu Cai,
  and Gordon Wetzstein (Stanford University); Or Litany (Technion); and Leo
 nidas Guibas (Stanford University)\n\nSymmetries are ubiquitous across all
  kinds of objects, whether in nature or in man-made creations. While these
  symmetries may seem intuitive to the human eye, detecting them with a mac
 hine is nontrivial due to the vast search space. Classical geometry-based 
 methods work by aggregating "votes" for each symmetry but struggle with no
 ise. In contrast, learning-based methods may be more robust to noise, but 
 often overlook partial symmetries due to the scarcity of annotated data. I
 n this work, we address this challenge by proposing a novel symmetry detec
 tion method that marries classical symmetry detection techniques with rece
 nt advances in generative modeling. Specifically, we apply Langevin dynami
 cs to a redefined symmetry space to enhance robustness against noise. We p
 rovide empirical results on a variety of shapes that suggest our method is
  not only robust to noise, but can also identify both partial and global s
 ymmetries. Moreover, we demonstrate the utility of our detected symmetries
  in various downstream tasks, such as compression and symmetrization of no
 isy shapes.\n\nRegistration Category: Full Access, Full Access Supporter\n
 \nLanguage Format: English Language\n\nSession Chair: Mirela Ben-Chen (Tec
 hnion – Israel Institute of Technology)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_1032&sess=sess133
END:VEVENT
END:VCALENDAR