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:20241205T130000
DTEND;TZID=Asia/Tokyo:20241205T141000
UID:siggraphasia_SIGGRAPH Asia 2024_sess130@linklings.com
SUMMARY:Neural Shapes
DESCRIPTION:Technical Papers\n\nEach Paper gives a 10 minute presentation.
 \n\nNeural Laplacian Operator for 3D Point Clouds\n\nThe Laplacian operato
 r holds a crucial role in 3D geometry processing, yet it is still challeng
 ing to define it on point clouds.\nPrevious works mainly focused on constr
 ucting a local triangulation around each point to approximate the underlyi
 ng manifold for defining the Laplacian operator, which may...\n\n\nBo Pang
 , Zhongtian Zheng, Yilong Li, Guoping Wang, and Peng-Shuai Wang (Peking Un
 iversity)\n---------------------\nNASM: Neural Anisotropic Surface Meshing
 \n\nThis paper introduces a new learning-based method, NASM, for anisotrop
 ic surface meshing. Our key idea is to propose a graph neural network to e
 mbed an input mesh into a high-dimensional (high-d) Euclidean embedding sp
 ace to preserve curvature-based anisotropic metric by using a dot product 
 loss bet...\n\n\nHongbo Li, Haikuan Zhu, and Sikai Zhong (Wayne State Univ
 ersity); Ningna Wang (University of Texas at Dallas); Cheng Lin (Universit
 y of Hong Kong); Xiaohu Guo (University of Texas at Dallas); Shiqing Xin (
 Shandong University); Wenping Wang (Texas A&M University); and Jing Hua an
 d Zichun Zhong (Wayne State University)\n---------------------\nDirect Man
 ipulation of Procedural Implicit Surfaces\n\nProcedural implicit surfaces 
 are a popular representation for shape modeling. They provide a simple fra
 mework for complex geometric operations such as Booleans, blending and def
 ormations. However, their editability remains a challenging task: as the d
 efinition of the shape is purely implicit, direct...\n\n\nMarzia Riso (Sap
 ienza University of Rome, Adobe); Élie Michel, Axel Paris, Valentin Descha
 intre, and Mathieu Gaillard (Adobe); and Fabio Pellacini (University of Mo
 dena and Reggio Emilia)\n---------------------\nControllable Shape Modelin
 g with Neural Generalized Cylinder\n\nNeural shape representation, such as
  neural signed distance field (NSDF), becomes more and more popular in sha
 pe modeling as its ability to deal with complex topology and arbitrary res
 olution. Due to the implicit manner to use features for shape representati
 on, manipulating the shapes faces inherent...\n\n\nXiangyu Zhu (Chinese Un
 iversity of Hong Kong, Shenzhen); Zhiqin Chen (Adobe Research); Ruizhen Hu
  (Shenzhen University (SZU)); and Xiaoguang Han (Chinese University of Hon
 g Kong, Shenzhen)\n---------------------\nSRIF: Semantic Shape Registratio
 n Empowered by Diffusion-based Image Morphing and Flow Estimation\n\nIn th
 is paper, we propose \textbf{SRIF}, a novel \textbf{S}emantic shape \textb
 f{R}egistration framework based on diffusion-based \textbf{I}mage morphing
  and \textbf{F}low Estimation. \nMore concretely, given a pair of extrinsi
 cally aligned shapes, we first render them from multi-views, and then we u
 ...\n\n\nMingze Sun (Tsinghua shenzhen international graduate school); Che
 n Guo and Puhua Jiang (Tsinghua shenzhen international graduate school, Pe
 ngcheng Lab); and Shiwei Mao, Yurun Chen, and Ruqi Huang (Tsinghua shenzhe
 n international graduate school)\n---------------------\nSpaceMesh: A Cont
 inuous Representation for Learning Manifold Surface Meshes\n\nMeshes are u
 biquitous in visual computing and simulation, yet most existing machine le
 arning techniques represent meshes only indirectly, e.g. as the level set 
 of a scalar field, or deformation of a template, or as a disordered triang
 le soup lacking local structure. This work presents a scheme to di...\n\n\
 nTianchang Shen (University of Toronto, NVIDIA Research) and Zhaoshuo Li, 
 Marc Law, Matan Atzmon, Sanja Fidler, James Lucas, Jun Gao, and Nicholas S
 harp (NVIDIA Research)\n\nRegistration Category: Full Access, Full Access 
 Supporter\n\nLanguage Format: English Language\n\nSession Chair: Noam Aige
 rman (University of Montreal)
END:VEVENT
END:VCALENDAR