BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030655Z
LOCATION:Meeting Room S426+S427\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251216T151100
DTEND;TZID=Asia/Hong_Kong:20251216T152200
UID:siggraphasia_SIGGRAPH Asia 2025_sess126_papers_1375@linklings.com
SUMMARY:Efficient Object Reconstruction with Differentiable Area Light Sha
 ding
DESCRIPTION:Yaoan Gao (State Key Laboratory of CAD&CG, Zhejiang University
 ); Jiamin Xu (Hangzhou Dianzi University); James Tompkin (Brown University
 ); Qi Wang (State Key Lab of CAD and CG, Zhejiang University); Zheng Dong 
 (Zhejiang Sci-Tech University; State Key Laboratory of CAD&CG, Zhejiang Un
 iversity); Hujun Bao (State Key Lab of CAD and CG, Zhejiang University); Y
 ujun Shen (Ant Group); Huamin Wang (Style3D Research, The Ohio State Unive
 rsity); Changqing Zou (State Key Laboratory of CAD&CG, Zhejiang University
 ; Zhejiang Lab); and Weiwei Xu (State Key Laboratory of CAD&CG, Zhejiang U
 niversity)\n\nIn 3D object reconstruction from photographs, estimating mat
 erial properties is challenging. We propose an inverse rendering method th
 at uses active area lighting: as this provides a wider range of lighting a
 ngles per photo than point lighting, material reconstruction can be more a
 ccurate for the same number of photos. We compare area light shading with 
 point lighting. With either mesh or 3D Gaussian splatting pipelines, area 
 lighting can improve BRDF reconstruction and leads to a relighting PSNR im
 provement of 3 dB, or alternatively needs 1/5 of the input photos for the 
 same quality as with point lights. We also compare area light shading with
  Monte Carlo ray tracing and with differential linearly transformed cosine
 s (LTC) plus shadow visibility weighting. LTC can be faster, improving opt
 imization times by 25%. In end-to-end method-level comparisons, our approa
 ch improves material reconstruction over SOTA methods, particularly for ma
 terial roughness, leading to superior relighting quality.\n\nRegistration 
 Category: Full Access, Full Access Supporter\n\nSession Chair: Zhouhui Lia
 n (Peking University, Wangxuan Institute of Computer Technology)\n\n
END:VEVENT
END:VCALENDAR
