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:20260817T171532Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T130000
DTEND;TZID=Asia/Tokyo:20241206T141000
UID:siggraphasia_SIGGRAPH Asia 2024_sess146@linklings.com
SUMMARY:Appearance Modeling
DESCRIPTION:Each Paper gives a 10 minute presentation.\n\nCorrelation-awar
 e Encoder-Decoder with Adapters for SVBRDF Acquisition\n\nCapturing materi
 als from the real world avoids laborious manual material authoring. Howeve
 r, recovering high-fidelity Spatially Varying Bidirectional Reflectance Di
 stribution Function (SVBRDF) maps from a few captured images is challengin
 g due to its ill-posed nature. Existing approaches have made e...\n\n\nDi 
 Luo and Hanxiao Sun (Nankai University), Lei Ma (Peking University), Jian 
 Yang (Nankai University), and Beibei Wang (Nanjing University)\n----------
 -----------\nNFPLight:  Deep SVBRDF Estimation via the Combination of Near
  and Far Field Point Lighting\n\nRecovering spatial-varying bi-directional
  reflectance distribution function (SVBRDF) from a few hand-held captured 
 images has been a challenging task in computer graphics. Benefiting from t
 he learned priors from data, single-image methods can obtain plausible SVB
 RDF estimation results. However, the ...\n\n\nLi Wang, Lianghao Zhang, Fan
 gzhou Gao, Yuzhen Kang, and Jiawan Zhang (Tianjin University)\n-----------
 ----------\nPolarimetric BSSRDF Acquisition of Dynamic Faces\n\nAcquisitio
 n and modeling of polarized light reflection and scattering help reveal th
 e shape, structure, and physical characteristics of an object, which is in
 creasingly important in computer graphics. However, current polarimetric a
 cquisition systems are limited to static and opaque objects. Human f...\n\
 n\nHyunho Ha and Inseung Hwang (Korea Advanced Institute of Science and Te
 chnology (KAIST)), Nestor Monzon (Universidad de Zaragoza - I3A), Jaemin C
 ho and Donggun Kim (Korea Advanced Institute of Science and Technology (KA
 IST)), Seung-Hwan Baek (POSTECH), Adolfo Muñoz and Diego Gutierrez (Univer
 sidad de Zaragoza - I3A), and Min H. Kim (Korea Advanced Institute of Scie
 nce and Technology (KAIST))\n---------------------\nControlMat: A Controll
 ed Generative Approach to Material Capture\n\nMaterial reconstruction from
  a photograph is a key component of 3D content creation democratization. W
 e propose to formulate this ill-posed problem as a controlled synthesis on
 e, leveraging the recent progress in generative deep networks. We present 
 ControlMat, a method which, given a single photogr...\n\n\nGiuseppe Vecchi
 o (Adobe Research, University of Catania) and Rosalie Martin, Arthur Roull
 ier, Adrien Kaiser, Romain Rouffet, Valentin Deschaintre, and Tamy Boubeke
 ur (Adobe Research)\n---------------------\nAppearance Modeling of Iridesc
 ent Feathers with Diverse Nanostructures\n\nMany animals exhibit structura
 l colors, which are often iridescent, meaning that the perceived colors ch
 ange with illumination conditions and viewing perspectives. Biological iri
 descence is usually caused by multilayers or other periodic structures in 
 animal tissues, which selectively reflect light ...\n\n\nYunchen Yu (Corne
 ll University); Andrea Weidlich (NVIDIA); Bruce Walter (Cornell University
 ); Eugene d'Eon (NVIDIA); and Steve Marschner (Cornell University, NVIDIA)
 \n---------------------\nA Dynamic By-example BTF Synthesis Scheme\n\nMeas
 ured Bidirectional Texture Function (BTF) can faithfully reproduce a reali
 stic appearance but is costly to acquire and store due to its 6D nature (2
 D spatial and 4D angular). Therefore, it is practical and necessary for re
 ndering to synthesize BTFs from a small example patch. While previous meth
 ...\n\n\nZilin Xu (University of California Santa Barbara), Zahra Montazer
 i (University of Manchester), Beibei Wang (Nanjing University), and Ling-Q
 i Yan (University of California Santa Barbara)\n\nRegistration Category: F
 ull Access, Full Access Supporter\n\nLanguage Format: English Language\n\n
 Session Chair: Valentin Deschaintre (Adobe Research)
END:VEVENT
END:VCALENDAR