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:20251218T030338Z
LOCATION:Meeting Room S221\, Level 2
DTSTART;TZID=Asia/Hong_Kong:20251215T145000
DTEND;TZID=Asia/Hong_Kong:20251215T155500
UID:siggraphasia_SIGGRAPH Asia 2025_sess111@linklings.com
SUMMARY:Neural & Implicit Representations for Geometry and Physics
DESCRIPTION:The Technical Papers program is the heartbeat of SIGGRAPH Asia
 , spotlighting world-class scholarly research at the forefront of computer
  graphics and interactive techniques. For decades, it has been the definit
 ive venue where bold ideas take root, foundational concepts are reimagined
 , and the future of visual computing is shaped.\n\nThis year, we explore n
 ew intersections of algorithms and artistry, automation and authorship, to
 ols and imagination – challenging the very way we design, simulate, visual
 ize, and interact with digital worlds.\n\nNeural Kinematic Bases for Fluid
 s\n\nWe propose mesh-free fluid simulations that exploit a kinematic neura
 l basis for velocity fields represented by an MLP. We design a set of loss
 es that ensures that these neural bases approximate fundamental physical p
 roperties such as orthogonality, divergence-free, boundary alignment, and 
 smoothnes...\n\n\nYibo Liu (University of Victoria), Zhixin Fang (Inworld 
 AI), Sune Darkner (University of Copenhagen), Noam Aigerman (University of
  Montreal), Kenny Erleben (University of Copenhagen), Paul Kry (McGill Uni
 versity), and Teseo Schneider (University of Victoria)\n------------------
 ---\nNeuVAS: Neural Implicit Surfaces for Variational Shape Modeling\n\nNe
 ural implicit shape representation has drawn significant attention in rece
 nt years due to its continuity, differentiability, and topological flexibi
 lity. However, directly modeling the shape of neural implicit fields, espe
 cially the neural signed distance function (SDF), with sparse geometric co
 nt...\n\n\nPengfei Wang (Shandong University); Qiujie Dong (University of 
 Hong Kong); Fangtian Liang (Shandong University); Hao Pan (Tsinghua Univer
 sity); Lei Yang (University of Hong Kong); Congyi Zhang (University of Bri
 tish Columbia); Guying Lin (University of Hong Kong); Caiming Zhang, Yuanf
 eng Zhou, Changhe Tu, and Shiqing Xin (Shandong University); Alla Sheffer 
 (University of British Columbia); and Xin Li and Wenping Wang (Texas A&M U
 niversity)\n---------------------\nPrecise Gradient Discontinuities in Neu
 ral Fields for Subspace Physics\n\nMany physical phenomena exhibit discont
 inuities in their spatial derivatives—such as folds in creased materials o
 r interfaces in heterogeneous solids—making their accurate representation 
 essential for high-fidelity simulation. Traditional approaches address suc
 h discontinuities by aligni...\n\n\nMengfei Liu, Yue Chang, and Zhecheng W
 ang (University of Toronto); Peter Yichen Chen (MIT CSAIL); and Eitan Grin
 spun (University of Toronto)\n---------------------\nVariational Neural Su
 rfacing of 3D Sketches\n\n3D sketches are an effective representation of a
  3D shape, convenient to create via modern Virtual or Augmented Reality (V
 R/AR) interfaces or from 2D sketches. For 3D sketches drawn by designers, 
 human observers can consistently imagine the surface they imply, yet recon
 structing such a surface with ...\n\n\nYutao Zhang (Université de Montréal
 ), Stephanie Wang (Adobe Research), and Mikhail Bessmeltsev (Université de
  Montréal)\n---------------------\nPractical Gaussian Process Implicit Sur
 faces with Sparse Convolutions\n\nA fundamental challenge in rendering has
  been the dichotomy between surface and volume models. Gaussian Process Im
 plicit Surfaces (GPISes) recently provided a unified approach for surfaces
 , volumes, and the spectrum in between. However, this representation remai
 ns impractical due to its high computa...\n\n\nKehan Xu (Dartmouth College
 ), Benedikt Bitterli and Eugene d'Eon (NVIDIA), and Wojciech Jarosz (Dartm
 outh College)\n---------------------\nNeural Octahedral Field: Octahedral 
 Prior for Simultaneous Smoothing and Sharp Edge Regularization\n\nNeural i
 mplicit representation, the parameterization of a continuous distance func
 tion as a Multi-Layer Perceptron (MLP), has emerged as a promising lead in
  tackling surface reconstruction from unoriented point clouds. In the pres
 ence of noise, however, its lack of explicit neighborhood connectivity...\
 n\n\nRuichen Zheng (Tsinghua University, Shenzhen University (SZU)); Tao Y
 u (Tsinghua University); and Ruizhen Hu (Shenzhen University (SZU))\n\nReg
 istration Category: Full Access, Full Access Supporter\n\nSession Chair: L
 igang Liu (University of Science and Technology of China)
END:VEVENT
END:VCALENDAR