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 1
DTSTART;TZID=America/Denver:20240729T090000
DTEND;TZID=America/Denver:20240729T103000
UID:siggraph_SIGGRAPH 2024_sess111@linklings.com
SUMMARY:Fast Radiance Fields
DESCRIPTION:StopThePop: Sorted Gaussian Splatting for View-consistent Real
 -time Rendering\n\nStopThePop, our novel hierarchical rasterizer, enhances
  3D Gaussian Splatting by eliminating popping artifacts caused by global s
 orting. Our proposed hierarchical, approximate per-pixel sort significantl
 y improves view-consistency for novel-view synthesis, while sophisticated 
 culling and load balanc...\n\n\nLukas Radl and Michael Steiner (Graz Unive
 rsity of Technology); Mathias Parger (Independent); Alexander Weinrauch (G
 raz University of Technology); Bernhard Kerbl (Technische Universität Wien
  (TU Wien)); and Markus Steinberger (Graz University of Technology, Huawei
  Technologies)\n---------------------\nRTG-SLAM: Real-time 3D Reconstructi
 on at Scale Using Gaussian Splatting\n\nRTG-SLAM is a real-time 3D reconst
 ruction system using Gaussian splatting. It is also memory efficient, enab
 ling reconstruction of large-scale environments. Comparisons demonstrate R
 TG-SLAM runs at around twice the speed of the state-of-the-art, NeRF-based
  SLAM, with around half the memory cost (e.g...\n\n\nZhexi Peng, Tianjia S
 hao, Yong Liu, and Jingke Zhou (Zhejiang University); Yin Yang (University
  of Utah); Jingdong Wang (Baidu Research); and Kun Zhou (Zhejiang Universi
 ty)\n---------------------\nFast Radiance Fields - Interactive Discussion\
 n\nAfter the summary presentations, attendees will participate in an inter
 active discussion. Distributed 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 related to their paper that could instigate further
  conver...\n\n---------------------\nA Hierarchical 3D Gaussian Representa
 tion for Real-time Rendering of Very Large Scenes\n\nWe introduce a hierar
 chy for 3D Gaussian splatting, merging primitives in a way that preserves 
 speed and quality. We divide the scene into chunks, each having a hierarch
 y that is further optimized. A consolidated hierarchy allows reconstructio
 n and real-time rendering of very large scenes of tens of...\n\n\nBernhard
  Kerbl (INRIA, Université Côte d'Azur; Technical University of Vienna); An
 dreas Meuleman and Georgios Kopanas (INRIA, Université Côte d'Azur); Micha
 el Wimmer (Technische Universität Wien (TU Wien)); and Alexandre Lanvin an
 d George Drettakis (Institut national de recherche en informatique et en a
 utomatique (INRIA), Unversité Côte d'Azur)\n---------------------\nBoostMV
 SNeRFs: Boosting MVS-based NeRFs to Generalizable View Synthesis in Large-
 scale Scenes\n\nBoostMVSNeRFs revolutionizes 3D scene visualization by imp
 roving the quality of large-scale MVS-based NeRFs. This innovative techniq
 ue combines multiple cost volumes with 3D visibility scores to enhance nov
 el view synthesis without additional training. Compatible with current fra
 meworks, it sets new...\n\n\nChih-Hai Su (National Yang Ming Chiao Tung Un
 iversity); Chih-Yao Hu (National Taiwan University); and Shr-Ruei Tsai, Ji
 e-Ying Lee, Chin-Yang Lin, and Yu-Lun Liu (National Yang Ming Chiao Tung U
 niversity)\n---------------------\nSMERF: Streamable Memory Efficient Radi
 ance Fields for Real-time Large-scene Exploration\n\nSMERF is a method for
  real-time view-synthesis of large, multi-room spaces on resource-constrai
 ned devices. By distilling state-of-the-art NeRF models into a compact, hi
 erarchical representation, SMERF enables the exploration of spaces as larg
 e as 300 m^2 with quality approaching that of its teacher...\n\n\nDaniel D
 uckworth (Google DeepMind); Peter Hedman (Google Research); Christian Reis
 er (Google Research; Tübingen AI Center, University of Tübingen); Peter Zh
 izhin (Google Research); Jean-François Thibert (Google AR/VR); Mario Lučić
  (Google DeepMind); and Richard Szeliski and Jonathan T. Barron (Google Re
 search)\n---------------------\n2D Gaussian Splatting for Geometrically Ac
 curate Radiance Fields\n\n2D Gaussian Splatting (2DGS) improves upon 3D Ga
 ussian Splatting (3DGS) by converting 3D volumes into 2D Gaussian disks. I
 t employs perspective-accurate 2D splatting, integrates depth distortion a
 nd normal consistency for improved reconstructions, and offers detailed ge
 ometry reconstruction with fas...\n\n\nBinbin Huang (ShanghaiTech Universi
 ty); Zehao Yu, Anpei Chen, and Andreas Geiger (University of Tübingen); an
 d Shenghua Gao (ShanghaiTech University)\n\nInterest Area: Research & Educ
 ation\n\nKeyword: Geometry, Modeling, Rendering\n\nRegistration Category: 
 Full Conference, Full Conference Supporter, Virtual Access, Exhibitor Full
  Conference, Monday\n\nSession Chair: Lin Gao (University of Chinese Acade
 my of Sciences)
END:VEVENT
END:VCALENDAR