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:20260417T190053Z
LOCATION:West Building\, Rooms 211-214
DTSTART;TZID=America/Los_Angeles:20250810T090000
DTEND;TZID=America/Los_Angeles:20250810T103000
UID:siggraph_SIGGRAPH 2025_sess175@linklings.com
SUMMARY:Real-Time and Mobile Techniques
DESCRIPTION:A Texture Streaming Pipeline for Real-Time GPU Ray Tracing\n\n
 Disney Animation makes heavy use of Ptex, which required a texture streami
 ng pipeline. The goal was to create a scalable system to provide a real-ti
 me experience even as the number of Ptex expand into thousands. We cap the
  maximum size of the GPU cache, and employ a LRU eviction scheme.\n\n\nMar
 k Lee, Nathan Zeichner, and Yining Karl Li (Walt Disney Animation Studios)
 \n---------------------\nAI-Powered Real-Time VFX for Mobile\n\nAI-Powered
  Real-Time VFX for Mobile explores the fusion of Generative Adversarial Ne
 tworks (GANs) and GPU particle systems to achieve cinematic-quality fire a
 nd water effects on mobile devices. The technology optimizes real-time ren
 dering across a wide range of hardware, enhancing mobile gaming and ...\n\
 n\nDomin Lee, Anda Li, and Kexin Lin (ByteDance Inc.)\n-------------------
 --\nRay Tracing with Bindless Vulkan on Mobile Devices, a Case Study: Perf
 ormance\n\nIn this talk, we’ll share our experience working with Vulkan bi
 ndless techniques and ray tracing on Android smartphones, overcoming hardw
 are constraints, driver issues, and other mobile platform limitations alon
 g the way. We'll also present a performance comparison across several Andr
 oid devic...\n\n\nSergey Kosarevsky, Roman Kuznetsov, and Alexey Medvedev 
 (Reality Labs, Meta)\n---------------------\nA Mobile Scanning Solution to
  Reconstruct Strand-Based Hairstyles\n\nWe propose a novel mobile scanning
  solution that allows end-users to reconstruct 3D hairstyles with actual p
 er-strand curves from just a phone scan. Using a mixture of deep learning 
 and optimization, we make hair scanning fast and accessible while deliveri
 ng qualitative assets ready to be used in an...\n\n\nPhilip-William Grassa
 l (Copresence AG), Luca Hormann and Nadia Hamlaoui (Copresence GmbH), Titu
 s Leistner (Copresence AG), and Lynton Ardizzone (Copresence GmbH)\n\nInte
 rest Area: Gaming & Interactive, New Technologies, Production & Animation\
 n\nRecording: Livestreamed, Not Livestreamed, Recorded, Not Recorded\n\nKe
 yword: Artificial Intelligence/Machine Learning, Augmented Reality, Captur
 e/Scanning, Digital Twins, Dynamics, Games, Generative AI, Modeling, Perfo
 rmance, Real-Time, Rendering, Simulation, Virtual Reality\n\nRegistration 
 Category: Full Conference, Virtual Access, Sunday\n\nSession Chair: Dave S
 hreiner (Unity Technologies, Sonoma State University)
END:VEVENT
END:VCALENDAR