BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260114T163731Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T101500
DTEND;TZID=Australia/Melbourne:20231215T111500
UID:siggraphasia_SIGGRAPH Asia 2023_sess154@linklings.com
SUMMARY:See Through The Field
DESCRIPTION:MCNeRF: Monte Carlo Rendering and Denoising for Real-Time NeRF
 s\n\nThe volume rendering step used in Neural Radiance Fields (NeRFs) prod
 uces highly photorealistic results, but is inherently slow because it eval
 uates an MLP at a large number of sample points per ray. Previous work has
  addressed this by either proposing neural scene representations that are 
 faster to...\n\n\nKunal Gupta (UC San Diego); Milos Hasan, Zexiang Xu, Fuj
 un Luan, Kalyan Sunkavalli, and Xin Sun (Adobe Inc.); Manmohan Chandraker 
 (UC San Diego); and Sai Bi (Adobe Inc.)\n---------------------\nAdaptive S
 hells for Efficient Neural Radiance Field Rendering\n\nNeural radiance fie
 lds achieve unprecedented quality for novel view synthesis, but their volu
 metric formulation remains expensive, requiring a huge number of samples t
 o render high-resolution images. Volumetric encodings are essential to rep
 resent fuzzy geometry such as foliage and hair, and they ar...\n\n\nZian W
 ang and Tianchang Shen (NVIDIA, University of Toronto); Merlin Nimier-Davi
 d and Nicholas Sharp (NVIDIA); Jun Gao (NVIDIA, University of Toronto); Al
 exander Keller (NVIDIA); Sanja Fidler (NVIDIA, University of Toronto); and
  Thomas Müller and Zan Gojcic (NVIDIA)\n---------------------\nScaNeRF: Sc
 alable Bundle-Adjusting Neural Radiance Fields for Large-Scale Scene Rende
 ring\n\nHigh-quality large-scale scene rendering requires a scalable repre
 sentation and accurate camera poses. This research combines tile-based hyb
 rid neural fields with parallel distributive optimization to improve bundl
 e-adjusting neural radiance fields. The proposed method scales with a divi
 de-and-conqu...\n\n\nXiuchao Wu (State Key Laboratory of CAD & CG, Zhejian
 g University); Jiamin Xu (Hangzhou Dianzi Univeristy); Xin Zhang (State Ke
 y Laboratory of CAD&CG, Zhejiang Univerisity); Hujun Bao (State Key Labora
 tory of CAD & CG, Zhejiang University); Qixing Huang (University of Texas 
 at Austin); Yujun Shen (Ant Group); James Tompkin (Brown University); and 
 Weiwei Xu (State Key Laboratory of CAD&CG, Zhejiang Univerisity)\n--------
 -------------\nActRay: Online Active Ray Sampling for Radiance Fields\n\nT
 hanks to the high-quality reconstruction and photorealistic rendering, the
  Neural Radiance Field (NeRF) has garnered extensive attention and has bee
 n continuously improved. Despite its high visual quality, the prohibitive 
 training time limits its practical application. Although significant accel
 era...\n\n\nJiangkai Wu, Liming Liu, Yunpeng Tan, Quanlu Jia, Haodan Zhang
 , and Xinggong Zhang (Peking University)\n---------------------\nRT-Octree
 : Accelerate PlenOctree Rendering with Batched Regular Tracking and Neural
  Denoising for Real-time Neural Radiance Fields\n\nNeural Radiance Fields 
 (NeRF) has demonstrated its ability to generate high-quality synthesized v
 iews. Nonetheless, due to its slow inference speed, there is a need to exp
 lore faster inference methods. In this paper, we propose RT-Octree, which 
 uses batched regular tracking based on PlenOctree with ...\n\n\nZixi Shu, 
 Ran Yi, Yuqi Meng, Yutong Wu, and Lizhuang Ma (Shanghai Jiao Tong Universi
 ty)\n\nRegistration Category: Full Access\n\nSession Chair: Yuchi Huo (Zhe
 jiang University, Korea Advanced Institute of Science and Technology)
END:VEVENT
END:VCALENDAR