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:20260417T190049Z
LOCATION:West Building\, Rooms 211-214
DTSTART;TZID=America/Los_Angeles:20250812T140000
DTEND;TZID=America/Los_Angeles:20250812T153000
UID:siggraph_SIGGRAPH 2025_sess103@linklings.com
SUMMARY:Reconstruction & Neural Fields
DESCRIPTION:Stochastic Preconditioning for Neural Field Optimization\n\nSt
 ochastic preconditioning adds spatial noise to query locations during neur
 al field optimization; it can be formalized as a stochastic estimate for a
  blur operator. This simple technique eases optimization and significantly
  improves quality for neural fields optimization, matching or outperformin
 g ...\n\n\nSelena Ling (NVIDIA, University of Toronto); Merlin Nimier-Davi
 d (NVIDIA); Alec Jacobson (University of Toronto); and Nicholas Sharp (NVI
 DIA)\n---------------------\nDiffusing Winding Gradients (DWG): A Parallel
  and Scalable Method for 3D Reconstruction from Unoriented Point Clouds\n\
 nDiffusing Winding Gradients (DWG) efficiently reconstructs watertight 3D 
 surfaces from unoriented point clouds. Unlike conventional methods, DWG av
 oids solving linear systems or optimizing objective functions, enabling si
 mple implementation and parallel execution. Our CUDA implementation on an 
 NVIDI...\n\n\nWeizhou Liu (Beijing Normal University); Jiaze Li (Nanyang T
 echnological University); Xuhui Chen and Fei Hou (Institute of Software, C
 hinese Academy of Sciences; University of Chinese Academy of Sciences); Sh
 iqing Xin (Shandong University); Xingce Wang and Zhongke Wu (Beijing Norma
 l University); Chen Qian (SenseTime Group); Ying He (Nanyang Technological
  University  College of Computing and Data Science); and Ying He\n--------
 -------------\nVariational Surface Reconstruction Using Natural Neighbors\
 n\nWe introduced a new surface reconstruction method from points without n
 ormals. The method robustly handles undersampled regions and scales to lar
 ge input sizes.\n\n\nJianjun Xia and Tao Ju (Washington University in St. 
 Louis)\n---------------------\nIMLS-Splatting: Efficient Mesh Reconstructi
 on from Multi-view Images via Point Representation\n\nWe propose IMLS-Spla
 tting, an end-to-end multi-view mesh optimization method that leverages po
 int clouds for surface representation. By introducing a splatting-based di
 fferentiable IMLS algorithm, our approach efficiently converts point cloud
 s into SDF and texture field, enabling multi-view mesh opt...\n\n\nKaizhi 
 Yang (University of Science and Technology of China); Liu Dai and Isabella
  Liu (University of California San Diego); Xiaoshuai Zhang (Hillbot Inc.);
  Xiaoyan Sun and Xuejin Chen (University of Science and Technology of Chin
 a); Zexiang Xu (Hillbot Inc.); and Hao Su (University of California San Di
 ego, Hillbot Inc.)\n---------------------\nSpline Deformation Field\n\nWe 
 combine splines,  a classical tool from applied mathematics, with implicit
  Coordinate Neural Networks to model deformation fields, achieving strong 
 performance across multiple datasets. The explicit regularization from spl
 ine interpolation enhances spatial coherency in challenging scenarios. We 
 f...\n\n\nMingyang Song (Disney Research Studios, ETH Zürich); Yang Zhang 
 (Disney Research Studios); Marko Mihajlovic and Siyu Tang (ETH Zürich); Ma
 rkus Gross (ETH Zürich, Disney Research Studios); and Tunc Ozan Aydin (Dis
 ney Research Studios)\n---------------------\nReconstruction & Neural Fiel
 ds - Interactive Discussion\n\nAfter the summary presentations, attendees 
 will participate in an interactive discussion. Outside the room will be a 
 series of poster boards for authors to gather around with the audience. Au
 thors are invited to bring any material related to their paper that could 
 instigate further conversation such...\n\n---------------------\nCAST: Com
 ponent-Aligned 3D Scene Reconstruction from an RGB Image\n\nWe introduce C
 AST, an innovative method for reconstructing high-quality 3D scenes from a
  single RGB  image. Supporting open-vocabulary reconstruction, CAST excels
  in managing occlusions, aligning objects accurately, and ensuring physica
 l consistency with the input, unlocking new possibilities in vir...\n\n\nK
 aixin Yao, Longwen Zhang, Xinhao Yan, Yan Zeng, and Qixuan Zhang (Shanghai
 Tech University, Deemos); Jiayuan Gu (ShanghaiTech University); Wei Yang (
 Huazhong University of Science and Technology); and Lan Xu and Jingyi Yu (
 ShanghaiTech University)\n\nInterest Area: Research & Education\n\nRecordi
 ng: Livestreamed, Not Livestreamed, Recorded, Not Recorded\n\nRegistration
  Category: Full Conference, Virtual Access, Tuesday\n\nSession Chair: Zhao
  Dong (Meta Reality Labs Research)
END:VEVENT
END:VCALENDAR