BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T171535Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T104500
DTEND;TZID=Asia/Tokyo:20241205T115500
UID:siggraphasia_SIGGRAPH Asia 2024_sess128@linklings.com
SUMMARY:Going Fast: Accelerated Rendering
DESCRIPTION:Each Paper gives a 10 minute presentation.\n\nAdR-Gaussian: Ac
 celerating Gaussian Splatting with Adaptive Radius\n\n3D Gaussian Splattin
 g (3DGS) is a recent explicit 3D representation that has achieved high-qua
 lity reconstruction and real-time rendering of complex scenes. However, th
 e rasterization pipeline still suffers from unnecessary overhead resulting
  from avoidable serial Gaussian culling, and uneven load d...\n\n\nXinzhe 
 Wang, Ran Yi, and Lizhuang Ma (Shanghai Jiao Tong University)\n-----------
 ----------\n3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes\n\nPa
 rticle-based representations of radiance fields such as 3D Gaussian Splatt
 ing have found great success for reconstructing and re-rendering of comple
 x scenes.\nMost existing methods render particles via rasterization, proje
 cting them to screen space tiles for processing in a sorted order.\nThis w
 ork ...\n\n\nNicolas Moenne-Loccoz (NVIDIA); Ashkan Mirzaei (NVIDIA, Unive
 rsity of Toronto); and Or Perel, Riccardo de Lutio, Janick Martinez Esturo
 , Gavriel State, Sanja Fidler, Nicholas Sharp, and Zan Gojcic (NVIDIA)\n--
 -------------------\nHigh-Throughput Batch Rendering for Embodied AI\n\nIn
  this paper we study the problem of efficiently rendering images for embod
 ied AI training workloads, where agent training involves rendering million
 s to billions of independent frames, often at low-resolutions and with sim
 ple (or no) lighting and shading, that serve as the agent's observations o
 f ...\n\n\nLuc Guy Rosenzweig, Brennan Shacklett, Warren Xia, and Kayvon F
 atahalian (Stanford University)\n---------------------\nEfficient Image-Sp
 ace Shape Splatting for Monte Carlo Rendering\n\nA typical Monte Carlo ren
 dering method contributes one light path only to a single pixel at a time.
  Reusing light paths across multiple pixels, however, can amortize the cos
 t and improve the efficiency. The state of the art of path reuse is to emp
 loy shift mapping to reduce the cost of path reuse, w...\n\n\nXiaochun Ton
 g and Toshiya Hachisuka (University of Waterloo)\n---------------------\nD
 irectL: Efficient Radiance Fields Rendering for 3D Light Field Displays\n\
 nAutostereoscopic display technology, despite decades of development, has 
 not achieved extensive application, primarily due to the daunting challeng
 e of three-dimensional (3D) content creation for non-specialists. The emer
 gence of Radiance Field as an innovative 3D representation has markedly re
 volut...\n\n\nZongyuan Yang, Baolin Liu, Yingde Song, Lan Yi, Yongping Xio
 ng, Zhaohe Zhang, and Xunbo Yu (Beijing University of Posts and Telecommun
 ications)\n\nRegistration Category: Full Access, Full Access Supporter\n\n
 Language Format: English Language\n\nSession Chair: Manolis Savva (Simon F
 raser University)
END:VEVENT
END:VCALENDAR