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:20241203T172800
DTEND;TZID=Asia/Tokyo:20241203T174000
UID:siggraphasia_SIGGRAPH Asia 2024_sess110_papers_1007@linklings.com
SUMMARY:Neural Global Illumination via Superposed Deformable Feature Field
 s
DESCRIPTION:Technical Papers\n\nChuankun Zheng, Yuchi Huo, Hongxiang Huang
 , and Hongtao Sheng (State Key Laboratory of CAD&CG, Zhejiang University);
  Junrong Huang (City University of Hong Kong); Rui Tang and Hao Zhu (Manyc
 ore Inc.); and Rui Wang and Hujun Bao (State Key Laboratory of CAD&CG, Zhe
 jiang University)\n\nInteractive rendering of dynamic scenes with complex 
 global illumination has been a long-standing problem in computer graphics.
 \nRecent advances in neural rendering demonstrate new promising possibilit
 ies.\nHowever, while existing methods have achieved impressive results, co
 mplex rendering effects (e.g., caustics) remain challenging.\nThis paper p
 resents a novel neural rendering method that is able to generate high-qual
 ity global illumination effects, including but not limited to caustics, so
 ft shadows, and indirect highlights, for dynamic scenes with varying camer
 a, lighting conditions, materials, and object transformations.\nInspired b
 y object-oriented transfer field representations, we employ deformable neu
 ral feature fields to implicitly model the impacts of individual objects o
 r light sources on global illumination.\nBy employing neural feature field
 s, our method gains the ability to represent high-frequency details, thus 
 supporting complex rendering effects.\nWe superpose these feature fields i
 n latent space and utilize a lightweight decoder to obtain global illumina
 tion estimates, which allows our neural representations to spontaneously a
 dapt to the contribution of individual objects or light sources to global 
 illumination in a data-driven manner, thus further improving the quality.\
 nOur experiments demonstrate the effectiveness of our method on a wide ran
 ge of scenes with complex light paths, materials, and geometry.\n\nRegistr
 ation Category: Full Access, Full Access Supporter\n\nLanguage Format: Eng
 lish Language\n\nSession Chair: Michael Wimmer (TU Wien)
URL:https://asia.siggraph.org/2024/program/?id=papers_1007&sess=sess110
END:VEVENT
END:VCALENDAR