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:20260817T171533Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241203T154300
DTEND;TZID=Asia/Tokyo:20241203T155400
UID:siggraphasia_SIGGRAPH Asia 2024_sess107_papers_826@linklings.com
SUMMARY:Local Gaussian Density Mixtures for Unstructured Lumigraph Renderi
 ng
DESCRIPTION:Xiuchao Wu (State Key Laboratory of CAD&CG, Zhejiang Universit
 y); Jiamin Xu (Hangzhou Dianzi Univeristy); Chi Wang (State Key Laboratory
  of CAD&CG, Zhejiang University); Yifan Peng (University of Hong Kong); Qi
 xing Huang (University of Texas at Austin); James Tompkin (Brown Universit
 y); and Weiwei Xu (State Key Laboratory of CAD&CG, Zhejiang University)\n\
 nTo improve novel-view synthesis of curved surface reflections and refract
 ions, we revisit local geometry-guided ray interpolation techniques with m
 odern differentiable rendering and optimization.\nIn contrast to depth or 
 mesh geometries, our approach uses a local or per-view density represented
  as Gaussian mixtures along each ray. \nTo synthesize novel views, we warp
  and fuse local volumes, then alpha-composite using input photograph ray c
 olors from a small set of neighboring images. \nFor fusion, we use a neura
 l blending weight from a shallow MLP. \nWe optimize the local Gaussian den
 sity mixtures using both a reconstruction loss and a consistency loss. \nT
 he consistency loss, based on per-ray KL-divergence, encourages more accur
 ate geometry reconstruction. \nOn scenes with complex reflections captured
  in our LGDM dataset, experimental results show that our method outperform
 s state-of-the-art novel-view synthesis methods by 12.2\%--37.1\% in PSNR,
  thanks to its ability to maintain sharper view-dependent appearance.\n\nR
 egistration Category: Full Access, Full Access Supporter\n\nLanguage Forma
 t: English Language\n\nSession Chair: Hongzhi Wu (Zhejiang University; Sta
 te Key Laboratory of CAD&CG, Zhejiang University)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_826&sess=sess107
END:VEVENT
END:VCALENDAR