BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260805T205456Z
LOCATION:Room 408 B
DTSTART;TZID=America/Los_Angeles:20260720T154500
DTEND;TZID=America/Los_Angeles:20260720T173500
UID:siggraph_SIGGRAPH 2026_sess146@linklings.com
SUMMARY:Creating & Iso-Surfacing SDFs
DESCRIPTION:Points as Tori: Fast Pointwise Signed Distance for Point Cloud
 s\n\nSigned distance computation has been either fast or robust, but not b
 oth. We explain why, using a theory that unifies signed distance with reco
 nstruction. Our method directly estimates signed distance from point cloud
 s, providing fast pointwise evaluation at arbitrary spatial resolution, wi
 thout req...\n\n\nNicole Feng and Ioannis Gkioulekas (Carnegie Mellon Univ
 ersity) and Keenan Crane (Carnegie Mellon University, Roblox Research)\n--
 -------------------\nSuperSDF:Sparse SDF Super-Resolution for Surface Extr
 action\n\nSuperSDF is a learning-based method for signed distance field su
 per-resolution that reconstructs high-fidelity meshes from coarse inputs, 
 without mesh supervision or auxiliary surface representations. Using a spa
 rse voxel network near the surface, our approach learns how to directly re
 fine the input...\n\n\nSagar Panwar and Nissim Maruani (INRIA), Céline Los
 cos (L Research), and Mathieu Desbrun and Pierre Alliez (INRIA)\n---------
 ------------\nSAND: Spatially Adaptive Network Depth for Fast Sampling of 
 Neural Implicit Surfaces\n\nSAND is an efficient neural implicit surface r
 epresentation framework  that accelerates sampling by adapting network dep
 th to spatial importance and local geometric complexity. By combining a vo
 lumetric depth map with a tailed MLP for adaptive termination, it signific
 antly improves inference-time qu...\n\n\nChuanxiang Yang (Shandong Univers
 ity), Junhui Hou (City University of Hong Kong), Yuan Liu (Hong Kong Unive
 rsity of Science and Technology), Siyu Ren (City University of Hong Kong),
  Guangshun Wei (Shandong University), Taku Komura (University of Hong Kong
 ), Yuanfeng Zhou (Shandong University), and Wenping Wang (Texas A&M Univer
 sity)\n---------------------\nThe PhaseTree: Multiphase Signed Distance Fi
 elds\n\nWe introduce the PhaseTree, a novel hierarchical construction tree
  representation for compactly modeling objects composed of multiple phases
  or materials. An object is defined as a single tree that combines phase-a
 ware primitives and operators, yielding a unified multiphase signed distan
 ce represent...\n\n\nEric Galin and Pierre Hubert-briere (Université Claud
 e Bernard Lyon 1, LIRIS); Marie-Paule Cani (Centre National de la Recherch
 e Scientifique - Laboratoire d'informatique de l'École Polytechnique (LIX)
 ); Adrien Peytavie (Université Claude Bernard Lyon 1, LIRIS); and Eric Gué
 rin and Hugo Schott (INSA, Lyon; LIRIS)\n---------------------\nDual Conto
 uring of Signed Distance Data\n\nWe propose an algorithm to reconstruct ex
 plicit polygonal meshes from discretely sampled Signed Distance Function (
 SDF) data, which is especially effective at recovering sharp features. Bui
 lding on the Dual Contouring of Hermite Data method, we solve a quadratic 
 optimization problem to place the mes...\n\n\nXiana Carrera and Ningna Wan
 g (Columbia University); Christopher Batty (University of Waterloo); Oded 
 Stein (Technion, University of Southern California); and Silvia Sellán (Co
 lumbia University)\n---------------------\nDual Contouring over Expanded C
 ubes (DCx) for Zero-Level Set Extraction from Neural Unsigned Distance Fun
 ctions\n\nDCx extends the Dual Contouring method which only extracts manif
 old surfaces from signed distance fields, to enable the surface extraction
  from unsigned distance fields. This is achieved by looking up a carefully
  designed table over expanded 2x2x2 cubes, allowing complex topologies to 
 be extracted, ...\n\n\nQingchao Bao and Xuhui Chen (Institute of Software,
  Chinese Academy of Sciences; University of Chinese Academy of Sciences); 
 Jingpeng Yin (Dalian University of Technology); Fei Hou and Wencheng Wang 
 (Institute of Software, Chinese Academy of Sciences; University of Chinese
  Academy of Sciences); Hong Qin (Stony Brook University); and Ying He (Nan
 yang Technological University (NTU))\n---------------------\nSubgrid March
 ing Tetrahedra\n\nSubgrid Marching Tetrahedra is an iso-surfacing method t
 hat reconstructs high quality surfaces while capturing fine topological fe
 atures below grid resolution. Using grid edge intersections locations with
  the implicit function, it produces manifold meshes with the usual benefit
 s from classical march...\n\n\nHossein Baktash (Carnegie Mellon University
 ); Mark Gillespie (INRIA, Saclay; University of Utah); and Keenan Crane (C
 arnegie Mellon University, Roblox)\n---------------------\nCreating & Iso-
 Surfacing SDFs - Interactive Discussion\n\nAfter the summary presentations
 , attendees will participate in an interactive discussion. Outside the roo
 m will be a series of poster boards for authors to gather around with the 
 audience. Authors are invited to bring any material related to their paper
  that could instigate further conversation such...\n\n\nInterest Area: Res
 earch & Education\n\nKeyword: Artificial Intelligence/Machine Learning, Ge
 ometry, Modeling\n\nRegistration Category: Full Conference Supporter, Full
  Conference\n\nSession Chair: Jernej Barbic (University of Southern Califo
 rnia)
END:VEVENT
END:VCALENDAR