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:20260817T171531Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T131100
DTEND;TZID=Asia/Tokyo:20241206T132300
UID:siggraphasia_SIGGRAPH Asia 2024_sess146_papers_928@linklings.com
SUMMARY:NFPLight:  Deep SVBRDF Estimation via the Combination of Near and 
 Far Field Point Lighting
DESCRIPTION:Li Wang, Lianghao Zhang, Fangzhou Gao, Yuzhen Kang, and Jiawan
  Zhang (Tianjin University)\n\nRecovering spatial-varying bi-directional r
 eflectance distribution function (SVBRDF) from a few hand-held captured im
 ages has been a challenging task in computer graphics. Benefiting from the
  learned priors from data, single-image methods can obtain plausible SVBRD
 F estimation results. However, the extremely limited appearance informatio
 n in a single image does not suffice for high-quality SVBRDF reconstructio
 n. Although increasing the number of inputs can improve the reconstruction
  quality, it also affects the efficiency of real data capture and adds sig
 nificant computational burdens. Therefore, the key challenge is to minimiz
 e the required number of inputs, while keeping high-quality results. To ad
 dress this, we propose maximizing the effective information in each input 
 through a novel co-located capture strategy that combines near-field and f
 ar-field point lighting. To further enhance effectiveness, we theoreticall
 y investigate the inherent relation between two images. The extracted rela
 tion is strongly correlated with the slope of specular reflectance, substa
 ntially enhancing the precision of roughness map estimation. Additionally,
  we designed the registration and denoising modules to meet the practical 
 requirements of hand-held capture. Quantitative assessments and qualitativ
 e analysis have demonstrated that our method achieves superior SVBRDF esti
 mations compared to previous approaches. All source codes will be publicly
  released.\n\nRegistration Category: Full Access, Full Access Supporter\n\
 nLanguage Format: English Language\n\nSession Chair: Valentin Deschaintre 
 (Adobe Research)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_928&sess=sess146
END:VEVENT
END:VCALENDAR