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:20250110T023312Z
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:Technical Papers\n\nEach Paper gives a 10 minute presentation.
 \n\nHigh-Throughput Batch Rendering for Embodied AI\n\nIn this paper we st
 udy the problem of efficiently rendering images for embodied AI training w
 orkloads, where agent training involves rendering millions to billions of 
 independent frames, often at low-resolutions and with simple (or no) light
 ing and shading, that serve as the agent's observations of ...\n\n\nLuc Gu
 y Rosenzweig, Brennan Shacklett, Warren Xia, and Kayvon Fatahalian (Stanfo
 rd University)\n---------------------\nAdR-Gaussian: Accelerating Gaussian
  Splatting with Adaptive Radius\n\n3D Gaussian Splatting (3DGS) is a recen
 t explicit 3D representation that has achieved high-quality reconstruction
  and real-time rendering of complex scenes. However, the rasterization pip
 eline still suffers from unnecessary overhead resulting from avoidable ser
 ial Gaussian culling, and uneven load d...\n\n\nXinzhe Wang, Ran Yi, and L
 izhuang Ma (Shanghai Jiao Tong University)\n---------------------\n3D Gaus
 sian Ray Tracing: Fast Tracing of Particle Scenes\n\nParticle-based repres
 entations of radiance fields such as 3D Gaussian Splatting have found grea
 t success for reconstructing and re-rendering of complex scenes.\nMost exi
 sting methods render particles via rasterization, projecting them to scree
 n space tiles for processing in a sorted order.\nThis work ...\n\n\nNicola
 s Moenne-Loccoz (NVIDIA); Ashkan Mirzaei (NVIDIA, University of Toronto); 
 and Or Perel, Riccardo de Lutio, Janick Martinez Esturo, Gavriel State, Sa
 nja Fidler, Nicholas Sharp, and Zan Gojcic (NVIDIA)\n---------------------
 \nEfficient Image-Space Shape Splatting for Monte Carlo Rendering\n\nA typ
 ical Monte Carlo rendering method contributes one light path only to a sin
 gle pixel at a time. Reusing light paths across multiple pixels, however, 
 can amortize the cost and improve the efficiency. The state of the art of 
 path reuse is to employ shift mapping to reduce the cost of path reuse, w.
 ..\n\n\nXiaochun Tong and Toshiya Hachisuka (University of Waterloo)\n----
 -----------------\nDirectL: Efficient Radiance Fields Rendering for 3D Lig
 ht Field Displays\n\nAutostereoscopic display technology, despite decades 
 of development, has not achieved extensive application, primarily due to t
 he daunting challenge of three-dimensional (3D) content creation for non-s
 pecialists. The emergence of Radiance Field as an innovative 3D representa
 tion has markedly revolut...\n\n\nZongyuan Yang, Baolin Liu, Yingde Song, 
 Lan Yi, Yongping Xiong, Zhaohe Zhang, and Xunbo Yu (Beijing University of 
 Posts and Telecommunications)\n\nRegistration Category: Full Access, Full 
 Access Supporter\n\nLanguage Format: English Language\n\nSession Chair: Ma
 nolis Savva (Simon Fraser University)
END:VEVENT
END:VCALENDAR