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:20260805T205509Z
LOCATION:Room 408 A
DTSTART;TZID=America/Los_Angeles:20260721T090000
DTEND;TZID=America/Los_Angeles:20260721T103000
UID:siggraph_SIGGRAPH 2026_sess135@linklings.com
SUMMARY:Fluid Reconstruction & Optimization
DESCRIPTION:GauSmoke: Hybrid Physics-Optical Gaussian Splatting for Sparse
  Smoke Reconstruction\n\nWe present a physics-aware method for reconstruct
 ing dynamic fluids from sparse-view videos. By integrating volumetric rend
 ering with physically guided Gaussian optimization, it enforces consistenc
 y in density and motion, reducing artifacts and improving realism. The app
 roach achieves accurate, stab...\n\n\nWenran Zhang and Yuxiang Cai (Nankai
  University); Letian Huang (State Key Lab for Novel Software Technology, N
 anjing University); Dongwei Ye and Jie Guo (Nanjing University); and Ren B
 o (Nankai University)\n---------------------\nLagrangianSplats: Divergence
 -Free Transport of Gaussian Primitives for Fluid Reconstruction\n\nLagrang
 ianSplats reconstructs physically plausible 3D fluid velocity fields from 
 sparse video by combining divergence-free kernels with Lagrangian Gaussian
  transport. A sliding-window optimization enables efficient long-range sup
 ervision, producing state-of-the-art transport consistency and physical...
 \n\n\nNingxiao Tao (School of Intelligence Science and Technology, Peking 
 University); Mengyu Chu (Peking University, State Key Laboratory of Genera
 l Artificial Intelligence); and Baoquan Chen (Peking University)\n--------
 -------------\nFast VEM Fluid Simulation\n\nFastVEM is an efficient bounda
 ry-conforming fluid simulation framework. It combines Virtual Element disc
 retization, a simulation-friendly body-fitted grid construction strategy, 
 and a tailored geometric multigrid method to achieve robust, high-fidelity
 , and efficient fluid–boundary interaction...\n\n\nRunze Zhang and Bo Ren 
 (Nankai University)\n---------------------\nDiffSurFlow: Efficient and Rob
 ust Differentiable Fluid Optimization via Surrogate Strategy on Flow Map\n
 \nWe present DiffSurFlow, an efficient and robust framework for long-horiz
 on and vortex-rich fluid optimization. Powered by a physics-informed surro
 gate gradient strategy that exploits flow map "gradient highways" while pr
 uning computationally intensive high-order gradient passes, it achieves si
 gnific...\n\n\nYuhao Quan, Hui Wang, Weile Lian, Zhi Wang, and Xubo Yang (
 Shanghai Jiao Tong University)\n---------------------\nGeneric Variational
  Spacetime Optimization of Vortex Core Manifolds\n\nWe introduce a highly 
 efficient variational framework for computing optimal vortex cores in 3D u
 nsteady flows. By unifying diverse detection criteria through time-preinte
 grated Lagrangians, our method accurately reconstructs spacetime vortex ma
 nifolds by solving Euler-Lagrange equations in just one ...\n\n\nXingdi Zh
 ang, Peter Rautek, and Markus Hadwiger (King Abdullah University of Scienc
 e and Technology (KAUST))\n---------------------\nFluid Reconstruction & O
 ptimization - Interactive Discussion\n\nAfter the summary presentations, a
 ttendees will participate in an interactive discussion. Outside the room w
 ill be a series of poster boards for authors to gather around with the aud
 ience. Authors are invited to bring any material related to their paper th
 at could instigate further conversation such...\n\n\nInterest Area: Resear
 ch & Education\n\nKeyword: Animation, Artificial Intelligence/Machine Lear
 ning, Real-Time, Rendering, Scientific Visualization, Simulation\n\nRegist
 ration Category: Full Conference Supporter, Full Conference\n\nSession Cha
 ir: Kui Wu (LIGHTSPEED)
END:VEVENT
END:VCALENDAR
