BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Brisbane
X-LIC-LOCATION:Australia/Brisbane
BEGIN:STANDARD
DTSTART:19920301T030000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20191203T080450Z
LOCATION:Plaza Meeting Room P2
DTSTART;TZID=Australia/Brisbane:20191118T112100
DTEND;TZID=Australia/Brisbane:20191118T114200
UID:siggraphasia_SIGGRAPH Asia 2019_sess104_papers_124@linklings.com
SUMMARY:Learning Efficient Illumination Multiplexing for Joint Capture of 
 Reflectance and Shape
DESCRIPTION:Technical Papers\n\nLearning Efficient Illumination Multiplexi
 ng for Joint Capture of Reflectance and Shape\n\nKang, Xie, He, Yi, Gu...\
 n\nWe propose a novel framework that automatically learns the lighting pat
 terns for efficient, joint acquisition of unknown reflectance and shape. T
 he core of our framework is a deep neural network, with a shared linear en
 coder that directly corresponds to the lighting patterns used in physical 
 acquisition, as well as non-linear decoders that output per-pixel normal a
 nd diffuse / specular information from photographs. We exploit the diffuse
  and normal information from multiple views to reconstruct a detailed 3D s
 hape, and then fit BRDF parameters to the diffuse / specular information, 
 producing texture maps as reflectance results. We demonstrate the effectiv
 eness of the framework with physical objects that vary considerably in ref
 lectance and shape, acquired with as few as 16~32 lighting patterns that c
 orrespond to 7~15 seconds of per-view acquisition time. Our framework is u
 seful for optimizing the efficiency in both novel and existing setups, as 
 it can automatically adapt to various factors, including the geometry / th
 e lighting layout of the device and the properties of appearance.\n\nRegis
 tration Category: Platinum Pass, Full Conference Pass, Full Conference One
 -Day Pass
URL:https://sa2019.conference-program.com/presentation?id=papers_124&sess=
 sess104
END:VEVENT
END:VCALENDAR