BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260805T205431Z
LOCATION:Hall K
DTSTART;TZID=America/Los_Angeles:20260719T180000
DTEND;TZID=America/Los_Angeles:20260719T204500
UID:siggraph_SIGGRAPH 2026_sess237_papers_1355@linklings.com
SUMMARY:Toward Richer Material Generation via Procedural Data Enhancement
DESCRIPTION:Yunchen Yu (Cornell University, NVIDIA); Jacob Munkberg, Jon H
 asselgren, and Chris Cummings (NVIDIA); Steve Marschner (Cornell Universit
 y, NVIDIA); and Andrea Weidlich (NVIDIA)\n\nGenerative material models are
  limited by simple PBR data. We augment single-lobe GGX materials into lay
 ered, multi-lobe models capturing richer effects (e.g., dust, clearcoat). 
 These are encoded as neural materials in a shared 6D latent space. The res
 ulting dataset enables generative models to produce more expressive materi
 als.\n\nInterest Area: Arts & Design, Gaming & Interactive, New Technologi
 es, Production & Animation, Research & Education\n\nKeyword: Animation, Ar
 t, Artificial Intelligence/Machine Learning, Audio, Augmented Reality, Cap
 ture/Scanning, Computer Vision, Digital Twins, Display, Dynamics, Educatio
 n, Ethics and Society, Fabrication, Games, Generative AI, Geometry, Haptic
 s, Hardware, Image Processing, Lighting, Math Foundations and Theory, Mode
 ling, Performance, Physical AI, Pipeline Tools and Work, Real-Time, Render
 ing, Robotics, Scientific Visualization, Simulation, Spatial Computing, Vi
 rtual Reality\n\nRegistration Category: Full Conference Supporter, Full Co
 nference, Experience\n\n
END:VEVENT
END:VCALENDAR
