BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035311Z
LOCATION:Room 324\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221208T140000
DTEND;TZID=Asia/Seoul:20221208T153000
UID:siggraphasia_SIGGRAPH Asia 2022_sess165_papers_242@linklings.com
SUMMARY:A Neural Galerkin Solver for Accurate Surface Reconstruction
DESCRIPTION:Technical Papers\n\nA Neural Galerkin Solver for Accurate Surf
 ace Reconstruction\n\nHuang, Chen, Hu\n\nTo reconstruct meshes from the wi
 dely-available 3D point cloud data, implicit shape representation is among
  the primary choices as an intermediate form due to its superior represent
 ation power and robustness in topological optimizations. Although differen
 t parameterizations of the implicit fields have been explored to model the
  underlying geometry, there is no explicit mechanism to ensure the fitting
  tightness of the surface to the input. We present in response, NeuralGale
 rkin, a neural Galerkin-method-based solver designed for reconstructing hi
 ghly-accurate surfaces from the input point clouds. NeuralGalerkin interna
 lly discretizes the target implicit field as a linear combination of a set
  of spatially-varying basis functions inferred by an adaptive sparse convo
 lution neural network. It then solves differentiably for a variational pro
 blem that incorporates both positional and normal constraints from the dat
 a in closed form within a single forward pass, highly respecting the raw i
 nput points. The reconstructed surface extracted from the implicit interpo
 lants is hence very accurate and incorporates useful inductive biases bene
 fiting from the training data. Extensive evaluations on various datasets d
 emonstrate our method's promising reconstruction performance and scalabili
 ty.\n\nRegistration Category: FULL ACCESS, ON-DEMAND ACCESS\n\nLanguage: E
 NGLISH\n\nFormat: IN-PERSON, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_242&sess=sess16
 5
END:VEVENT
END:VCALENDAR