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:20250110T023309Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241203T145600
DTEND;TZID=Asia/Tokyo:20241203T150800
UID:siggraphasia_SIGGRAPH Asia 2024_sess107_papers_238@linklings.com
SUMMARY:GS^3: Efficient Relighting with Triple Gaussian Splatting
DESCRIPTION:Technical Papers\n\nZoubin Bi, Yixin Zeng, Chong Zeng, Fan Pei
 , Xiang Feng, Kun Zhou, and Hongzhi Wu (State Key Laboratory of CAD&CG, Zh
 ejiang University)\n\nWe present a spatial and angular Gaussian based repr
 esentation and a triple splatting process, for real-time, high-quality nov
 el lighting-and-view synthesis from multi-view point-lit input images. To 
 describe complex appearance, we employ a Lambertian plus a mixture of angu
 lar Gaussians as an effective reflectance function for each spatial Gaussi
 an. To generate self-shadow, we splat all spatial Gaussians towards the li
 ght source to obtain shadow values, which are further refined by a small m
 ulti-layer perceptron. To compensate for other effects like global illumin
 ation, another network is trained to compute and add a per-spatial-Gaussia
 n RGB tuple. The effectiveness of our representation is demonstrated on 30
  samples with a wide variation in geometry (from solid to fluffy) and appe
 arance (from translucent to anisotropic), as well as using different forms
  of input data, including rendered images of synthetic/reconstructed objec
 ts, photographs captured with a handheld camera and a flash, or from a pro
 fessional lightstage. We achieve a training time of 40-70 minutes and a re
 ndering speed of 90 fps on a single commodity GPU. Our results compare fav
 orably with state-of-the-art techniques in terms of quality/performance.\n
 \nRegistration Category: Full Access, Full Access Supporter\n\nLanguage Fo
 rmat: English Language\n\nSession Chair: Hongzhi Wu (Zhejiang University; 
 State Key Laboratory of CAD&CG, Zhejiang University)
URL:https://asia.siggraph.org/2024/program/?id=papers_238&sess=sess107
END:VEVENT
END:VCALENDAR