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:20241205T131100
DTEND;TZID=Asia/Tokyo:20241205T132300
UID:siggraphasia_SIGGRAPH Asia 2024_sess130_papers_1233@linklings.com
SUMMARY:NASM: Neural Anisotropic Surface Meshing
DESCRIPTION:Technical Papers\n\nHongbo Li, Haikuan Zhu, and Sikai Zhong (W
 ayne State University); Ningna Wang (University of Texas at Dallas); Cheng
  Lin (University of Hong Kong); Xiaohu Guo (University of Texas at Dallas)
 ; Shiqing Xin (Shandong University); Wenping Wang (Texas A&M University); 
 and Jing Hua and Zichun Zhong (Wayne State University)\n\nThis paper intro
 duces a new learning-based method, NASM, for anisotropic surface meshing. 
 Our key idea is to propose a graph neural network to embed an input mesh i
 nto a high-dimensional (high-d) Euclidean embedding space to preserve curv
 ature-based anisotropic metric by using a dot product loss between high-d 
 edge vectors. This can dramatically reduce the computational time and incr
 ease the scalability. Then, we propose a novel feature-sensitive remeshing
  on the generated high-d embedding to automatically capture sharp geometri
 c features. We define a high-d normal metric, and then derive an automatic
  differentiation on a high-d centroidal Voronoi tessellation (CVT) optimiz
 ation with the normal metric to simultaneously preserve geometric features
  and curvature anisotropy that exhibit in the original 3D shapes. To our k
 nowledge, this is the first time that a deep learning framework and a larg
 e dataset are proposed to construct a high-d Euclidean embedding space for
  3D anisotropic surface meshing. Experimental results are evaluated and co
 mpared with the state-of-the-art in anisotropic surface meshing on a large
  number of surface models from Thingi10K dataset as well as tested on exte
 nsive unseen 3D shapes from Multi-Garment Network dataset and FAUST human 
 dataset.\n\nRegistration Category: Full Access, Full Access Supporter\n\nL
 anguage Format: English Language\n\nSession Chair: Noam Aigerman (Universi
 ty of Montreal)
URL:https://asia.siggraph.org/2024/program/?id=papers_1233&sess=sess130
END:VEVENT
END:VCALENDAR