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:20260114T163652Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T103000
DTEND;TZID=Australia/Melbourne:20231215T104500
UID:siggraphasia_SIGGRAPH Asia 2023_sess154_papers_485@linklings.com
SUMMARY:ScaNeRF: Scalable Bundle-Adjusting Neural Radiance Fields for Larg
 e-Scale Scene Rendering
DESCRIPTION:Xiuchao Wu (State Key Laboratory of CAD & CG, Zhejiang Univers
 ity); Jiamin Xu (Hangzhou Dianzi Univeristy); Xin Zhang (State Key Laborat
 ory of CAD&CG, Zhejiang Univerisity); Hujun Bao (State Key Laboratory of C
 AD & 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\nHigh-quality la
 rge-scale scene rendering requires a scalable representation and accurate 
 camera poses. This research combines tile-based hybrid neural fields with 
 parallel distributive optimization to improve bundle-adjusting neural radi
 ance fields. The proposed method scales with a divide-and-conquer strategy
 . We partition scenes into tiles, each with a multi-resolution hash featur
 e grid and shallow chained diffuse and specular multi-layer perceptrons (M
 LPs). Tiles unify foreground and background via a spatial contraction func
 tion that allows both distant objects in outdoor scenes and planar reflect
 ions as virtual images outside the tile. Decomposing appearance with the s
 pecular MLP allows a specular-aware warping loss to provide a second optim
 ization path for camera poses. We apply the alternating direction method o
 f multipliers (ADMM) to achieve consensus among camera poses while maintai
 ning parallel tile optimization. Experimental results show that our method
  outperforms state-of-the-art neural scene rendering method quality by 5%-
 -10% in PSNR, maintaining sharp distant objects and view-dependent reflect
 ions across six indoor and outdoor scenes.\n\nRegistration Category: Full 
 Access\n\nSession Chair: Yuchi Huo (Zhejiang University, Korea Advanced In
 stitute of Science and Technology)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_485&sess=sess154
END:VEVENT
END:VCALENDAR