BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250522T212948Z
LOCATION:Mile High 2A
DTSTART;TZID=America/Denver:20240801T090000
DTEND;TZID=America/Denver:20240801T103000
UID:siggraph_SIGGRAPH 2024_sess134@linklings.com
SUMMARY:Spatial Data Structures
DESCRIPTION:Neural Gaussian Scale-space Fields\n\nWe present a method to l
 earn a fully continuous Gaussian scale-space from raw data. This allows ef
 ficient and flexible anisotropic filtering and can be used to create multi
 scale representations across a broad range of modalities and applications.
 \n\n\nFelix Mujkanovic, Ntumba Elie Nsampi, Christian Theobalt, Hans-Peter
  Seidel, and Thomas Leimkühler (Max Planck Institute for Informatics)\n---
 ------------------\nNeuralVDB: High-resolution Sparse Volume Representatio
 n using Hierarchical Neural Networks\n\nNeuralVDB enhances the VDB framewo
 rk for efficient sparse volumetric data storage by integrating machine lea
 rning. This new structure significantly reduces memory usage while maintai
 ning flexibility with minimal compression errors. It combines a shallow VD
 B tree with hierarchical neural networks for...\n\n\nDoyub Kim, Minjae Lee
 , and Ken Museth (NVIDIA, USA) and Doyub Kim\n---------------------\nN-BVH
 : Neural Ray Queries With Bounding Volume Hierarchies\n\nN-BVH, a compress
 ed neural architecture, enables efficient ray queries in rendering. Our me
 thod seamlessly integrates neural ray queries into standard pipelines. By 
 optimizing parameters through an adaptive BVH-driven probing scheme, N-BVH
  can serve accurate ray queries from a compact representation...\n\n\nPhil
 ippe Weier (Saarland Informatics Campus, DFKI); Alexander Rath (DFKI, Saar
 land Informatics Campus); Élie Michel and Iliyan Georgiev (Adobe); Philipp
  Slusallek (DFKI); and Tamy Boubekeur (Adobe)\n---------------------\nSpat
 ial Data Structures - Interactive Discussion\n\nAfter the summary presenta
 tions, attendees will participate in an interactive discussion. Distribute
 d around 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 conver...\n\n---------------
 ------\nfVDB : A Deep-learning Framework for Sparse, Large Scale, and High
  Performance Spatial Intelligence\n\nWe introduce fVDB, a GPU-optimized fr
 amework for deep learning on large-scale 3D data that efficiently accommod
 ates spatial sparsity, based on a novel VDB index grid structure. Our fram
 ework is fully integrated with PyTorch and includes a comprehensive collec
 tion of operators for tasks such as convo...\n\n\nFrancis Williams, Jiahui
  Huang, Jonathan Swartz, Gergely Klar, Vijay Thakkar, Matthew Cong, and Xu
 anchi Ren (NVIDIA Research); Ruilong Li (NVIDIA Research, University of Ca
 lifornia Berkeley); Clement Fuji Tsang and Sanja Fidler (NVIDIA Research);
  Eftychios Sifakis (University of Wisconsin-Madison, NVIDIA Research); and
  Ken Museth (NVIDIA Research)\n---------------------\nNeural Bounding\n\nO
 ur research introduces a neural approach to bounding volumes, conservative
 ly classifying space across diverse dimensions and scenes. The key is a no
 vel loss function that produces minimal false negatives. Our method extend
 s to non-neural and hybrid representations. We also propose an early exit 
 str...\n\n\nStephanie Wenxin Liu (Birkbeck, University of London); Michael
  Fischer (University College London (UCL)); Paul D. Yoo (Birkbeck, Univers
 ity of London); and Tobias Ritschel (University College London (UCL))\n---
 ------------------\nReFiNe: Recursive Field Networks for Cross-modal Multi
 -scene Representation\n\nThe common trade-offs of state-of-the-art methods
  for multi-shape representation involve trading modeling accuracy against 
 memory and storage. We show how a recursive hierarchical architecture can 
 be used to encode multiple shapes represented as continuous neural fields 
 with a higher degree of preci...\n\n\nSergey Zakharov, Katherine Liu, Adri
 en Gaidon, and Rares Ambrus (Toyota Research Institute)\n\nInterest Area: 
 Research & Education\n\nKeyword: Geometry, Modeling\n\nRegistration Catego
 ry: Full Conference, Full Conference Supporter, Virtual Access, Exhibitor 
 Full Conference, Thursday\n\nSession Chair: Tizian Zeltner (NVIDIA)
END:VEVENT
END:VCALENDAR