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:20240214T070241Z
LOCATION:Darling Harbour Theatre\, Level 2 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T093000
DTEND;TZID=Australia/Melbourne:20231212T124500
UID:siggraphasia_SIGGRAPH Asia 2023_sess209_papers_538@linklings.com
SUMMARY:MatFusion: A Generative Diffusion Model for SVBRDF Capture
DESCRIPTION:Technical Papers\n\nSam Sartor and Pieter Peers (College of Wi
 lliam & Mary)\n\nWe formulate SVBRDF estimation from photographs as a diff
 usion task. To model the distribution of spatially varying materials, we f
 irst train a novel unconditional SVBRDF diffusion backbone model on a larg
 e set of 312,165 synthetic spatially varying material exemplars.  This SVB
 RDF  diffusion backbone model, named MatFusion, can then serve as a basis 
 for refining a conditional diffusion model to estimate the material proper
 ties from a photograph under controlled or uncontrolled lighting. Our back
 bone MatFusion model is trained using only a loss on the reflectance prope
 rties,  and therefore refinement can be paired with more expensive renderi
 ng methods without the need for backpropagation during training.  Because 
 the conditional SVBRDF diffusion models are generative, we can synthesize 
  multiple SVBRDF estimates from the same input photograph from which the u
 ser can select the one that best matches the users' expectation.  We demon
 strate the flexibility of our method by refining different SVBRDF diffusio
 n models conditioned on different types of incident lighting, and show tha
 t for a single photograph under colocated flash lighting our method achiev
 es equal or better accuracy than existing SVBRDF estimation methods.\n\nRe
 gistration Category: Full Access, Enhanced Access, Trade Exhibitor, Experi
 ence Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=papers_538&sess=sess209
END:VEVENT
END:VCALENDAR