BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240214T070311Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T162500
DTEND;TZID=Australia/Melbourne:20231214T171800
UID:siggraphasia_SIGGRAPH Asia 2023_sess133@linklings.com
SUMMARY:Visualizing the Future
DESCRIPTION:Technical Communications, Technical Papers\n\nDiffusion-based 
 Holistic Texture Rectification and Synthesis\n\nWe present a novel framewo
 rk for rectifying occlusions and distortions in degraded texture samples f
 rom natural images. Traditional texture synthesis approaches focus on gene
 rating textures from pristine samples, which necessitate meticulous prepar
 ation by humans and are often unattainable in most n...\n\n\nGuoqing Hao (
 University of Tsukuba, National Institute of Advanced Industrial Science a
 nd Technology); Satoshi Iizuka (University of Tsukuba); Kensho Hara (Natio
 nal Institute of Advanced Industrial Science); Edgar Simo-Serra (Waseda Un
 iversity); Hirokatsu Kataoka (National Institute of Advanced Industrial Sc
 ience); and Kazuhiro Fukui (University of Tsukuba)\n---------------------\
 nMatFusion: A Generative Diffusion Model for SVBRDF Capture\n\nWe formulat
 e SVBRDF estimation from photographs as a diffusion task. To model the dis
 tribution of spatially varying materials, we first train a novel unconditi
 onal SVBRDF diffusion backbone model on a large set of 312,165 synthetic s
 patially varying material exemplars.  This SVBRDF  diffusion backbo...\n\n
 \nSam Sartor and Pieter Peers (College of William & Mary)\n---------------
 ------\nDeepBasis: Hand-Held Single-Image SVBRDF Capture via Two-Level Bas
 is Material Model\n\nRecovering spatial-varying bi-directional reflectance
  distribution function (SVBRDF) from a single hand-held captured image has
  been a meaningful but challenging task in computer graphics. Benefiting f
 rom the learned data priors, some previous methods can utilize the potenti
 al material correlations ...\n\n\nLi Wang, Lianghao Zhang, Fangzhou Gao, a
 nd Jiawan Zhang (Tianjin University)\n---------------------\nMicroGlam: Mi
 croscopic Skin Image Dataset with Cosmetics\n\nIn this paper, we present a
  cosmetic-specific skin image dataset. It consists of skin images from 45 
 patches of size 8mm*8mm under three cosmetic products (i.e. foundation, bl
 usher, and highlighter).\n\n\nToby Chong (The University of Toko), Alina C
 hadwick (Dartmouth College), I-Chao Shen (The University of Tokyo), Haoran
  Xie (Japan Advanced Institute of Science and Technology (JAIST)), and Tak
 eo Igarashi (The University of Tokyo)\n---------------------\nOpenSVBRDF: 
 A Database of Measured Spatially-Varying Reflectance\n\nWe present the fir
 st large-scale database of measured spatially-varying anisotropic reflecta
 nce, consisting of 1,000 high-quality near-planar SVBRDFs, spanning 9 mate
 rial categories such as wood, fabric and metal. Each sample is captured in
  15 minutes, and represented as a set of high-resolution tex...\n\n\nXiaoh
 e Ma, Xianmin Xu, Leyao Zhang, Kun Zhou, and Hongzhi Wu (State Key Laborat
 ory of CAD&CG, Zhejiang Univerisity)\n\nRegistration Category: Full Access
 \n\nSession Chair: Anton Kaplanyan (Intel)
END:VEVENT
END:VCALENDAR