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:20260417T190111Z
LOCATION:West Building\, Rooms 301-305
DTSTART;TZID=America/Los_Angeles:20250811T104500
DTEND;TZID=America/Los_Angeles:20250811T121500
UID:siggraph_SIGGRAPH 2025_sess105@linklings.com
SUMMARY:Reconstruct it All
DESCRIPTION:Reconstruct it All - Interactive Discussion\n\nAfter the summa
 ry 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. Authors are invited to bring any material relate
 d to their paper that could instigate further conversation such...\n\n----
 -----------------\nNeST: Neural Stress Tensor Tomography by leveraging 3D 
 Photoelasticity\n\nNeST enables non-destructive 3D stress analysis of tran
 sparent objects using the polarization of light. Traditional 2D methods re
 quire destructively slicing the object. Instead, we reconstruct the entire
  3D stress field by jointly handling phase unwrapping and tensor tomograph
 y using neural implicit...\n\n\nAkshat Dave (Massachusetts Institute of Te
 chnology Media Lab), Tianyi Zhang (Rice University), Aaron Young and Rames
 h Raskar (Massachusetts Institute of Technology Media Lab), Wolfgang Heidr
 ich (King Abdullah University of Science and Technology), Ashok Veeraragha
 van (Rice University), and Akshat Dave\n---------------------\nEchoes of t
 he Coliseum: Towards 3D Live streaming of Sports Events\n\nWe present a re
 volutionary method for experiencing live sports in stunning 3D, redefining
  the way games are seen, through immersive, interactive replays. Alongside
 , we release a large-scale synthetic dataset built to benchmark realism, m
 otion, and human interaction in dynamic scenes, to fuel the nex...\n\n\nJu
 nkai Huang, Saswat Subhajyoti Mallick, Alejandro Amat, Marc Ruiz Olle, Alb
 ert Mosella-Montoro, Bernhard Kerbl, Francisco Vicente Carrasco, and Ferna
 ndo De la Torre (Carnegie Mellon University)\n---------------------\nRadia
 nce Surfaces: Optimizing Surface Representations with a 5D Radiance Field 
 Loss\n\nWe present a simple and fast method to reconstruct radiance surfac
 es by directly supervising the radiance field via image projection. \nUnli
 ke volumetric approaches, we move alpha blending and ray marching from ima
 ge formation into loss computation. \nThis simple modification enables hig
 h-quality surf...\n\n\nZiyi Zhang and Nicolas Roussel (EPFL); Thomas Mulle
 r, Tizian Zeltner, Merlin Nimier-David, and Fabrice Rousselle (NVIDIA); an
 d Wenzel Jakob (EPFL)\n---------------------\nSplat and Replace: 3D Recons
 truction with Repetitive Elements\n\nWe leverage repetitions in 3D scenes 
 to improve reconstruction in low-quality parts due to poor coverage and oc
 clusions. Our methods segments the repetitions, registers them together, a
 nd optimizes a shared representation with multi-view information flowing f
 rom all repetitions, improving the recons...\n\n\nNicolas Violante, Andréa
 s Meuleman, and Alban Gauthier (INRIA, Université Côte d'Azur); Fredo Dura
 nd (Massachusetts Institute of Technology (MIT)); Thibault Groueix (Adobe 
 Research); and George Drettakis (INRIA, Université Côte d'Azur)\n---------
 ------------\nSpotLessSplats: Ignoring Distractors in 3D Gaussian Splattin
 g\n\n3D Gaussian Splatting (3DGS) enables fast 3D reconstruction and rende
 ring but struggles with real-world captures due to transient elements and 
 lighting changes. We introduce SpotLessSplats, which leverages semantic fe
 atures from foundation models and robust optimization to remove transient 
 effects, ...\n\n\nSara Sabour (Google Inc - Deepmind, University of Toront
 o); Lily Goli (University of Toronto); George Kopanas (Runway); Mark Matth
 ews and Dmitry Lagun (Google Inc - Deepmind); Leonidas Guibas (Google Inc 
 - Deepmind, Stanford University); Alec Jacobson (University of Toronto); D
 avid Fleet (Google Inc - Deepmind, University of Toronto); Andrea Tagliasa
 cchi (Google Inc - Deepmind, Simon Fraser University); and Sara Sabour and
  Lily Goli\n\nInterest Area: Research & Education\n\nRecording: Livestream
 ed, Not Livestreamed, Recorded, Not Recorded\n\nRegistration Category: Ful
 l Conference, Virtual Access, Monday\n\nSession Chair: Szymon Rusinkiewicz
  (Princeton University)
END:VEVENT
END:VCALENDAR