BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250522T212948Z
LOCATION:Mile High 3C
DTSTART;TZID=America/Denver:20240731T090000
DTEND;TZID=America/Denver:20240731T103000
UID:siggraph_SIGGRAPH 2024_sess123@linklings.com
SUMMARY:Real-Time Rendering: Hair, Fabrics, and Super-Resolution
DESCRIPTION:Real-time Hair Rendering With Hair Meshes\n\nWe present how th
 e hair mesh structure can be used for efficiently rendering strand-based h
 air models on the GPU. We demonstrate an unprecedented level of performanc
 e for real-time hair rendering, allowing scenes involving hundreds of char
 acters with full-resolution unique hair models at real-time f...\n\n\nGaur
 av Bhokare (University of Utah); Eisen Montalvo (University of Utah, RTX);
  Elie Diaz (University of Utah); and Cem Yuksel (Cyber Radiance)\n--------
 -------------\nModeling Hair Strands With Roving Capsules\n\nThe paper der
 ives a parametric representation for swept sphere shapes and proposes an e
 fficient ray-surface intersection algorithm using capsules that are dynami
 cally defined per ray at runtime. This new algorithm is more than twice as
  fast as previous approaches and can be used for hair and fur ren...\n\n\n
 Alexander Reshetov and David Hart (NVIDIA)\n---------------------\nReal-ti
 me Physically Guided Hair Interpolation\n\nLinear interpolation can often 
 cause severe deformation artifacts in hair for which alternatives often en
 tail expensive training or precomputation. Instead, we present a novel for
 ce-based hair interpolation scheme to leverage existing real-time simulati
 on data for a robust interpolation with very li...\n\n\nJerry Hsu (Univers
 ity of Utah, LightSpeed Studios); Tongtong Wang, Zherong Pan, and Xifeng G
 ao (LightSpeed Studios); Cem Yuksel (University of Utah, Roblox); and Kui 
 Wu (LightSpeed Studios)\n---------------------\nReal-Time Rendering: Hair,
  Fabrics, and Super-Resolution - Interactive Discussion\n\nAfter the summa
 ry presentations, attendees will participate in an interactive discussion.
  Distributed around the room will be a series of poster boards for authors
  to gather around with the audience. Authors are invited to bring any mate
 rial related to their paper that could instigate further conver...\n\n----
 -----------------\nReal-time Neural Woven Fabric Rendering\n\nWe propose a
  lightweight neural network to represent woven fabrics at different scales
  in real time. By encoding the regular and repetitive woven fabric pattern
  into a small latent vector, our network is able to handle three typical t
 ypes of woven fabrics in our training dataset: plain, twill, and s...\n\n\
 nXiang Chen and Lu Wang (Shandong University) and Beibei Wang (Nanjing Uni
 versity)\n---------------------\nMob-FGSR: Frame Generation and Super Reso
 lution for Mobile Real-time Rendering\n\nWe propose Mob-FGSR, a lightweigh
 t supersampling framework designed specifically for mobile devices, integr
 ating frame generation with super-resolution to significantly enhance real
 -time rendering performance. This method operates efficiently without high
 -end GPUs or dedicated hardware, surpassing o...\n\n\nSipeng Yang, Qingchu
 an Zhu, and Junhao Zhuge (State Key Laboratory of CAD & CG, Zhejiang Unive
 rsity); Qiang Qiu, Chen Li, Yuzhong Yan, and Huihui Xu (OPPO Computing & G
 raphics Research Institute); Ling-Qi Yan (University of California Santa B
 arbara); and Xiaogang Jin (Zhejiang University; State Key Lab of CAD&CG, Z
 hejiang University)\n---------------------\nDeep Fourier-based Arbitrary-s
 cale Super-resolution for Real-time Rendering\n\nBy observing that high-re
 solution G-buffers possess similar spectrum to high-resolution rendered fr
 ame, we propose a method by supporting arbitrary-scale super-resolution fo
 r a trained neural model. The key is a Fourier-based implicit neural repre
 sentation which maps arbitrary and naturally continuo...\n\n\nHaonan Zhang
 , Jie Guo, Jiawei Zhang, Haoyu Qin, Zesen Feng, Ming Yang, and Yanwe Guo (
 Nanjing University)\n\nInterest Area: Research & Education\n\nKeyword: Rea
 l-Time, Rendering\n\nRegistration Category: Full Conference, Full Conferen
 ce Supporter, Virtual Access, Exhibitor Full Conference, Wednesday\n\nSess
 ion Chair: Iliyan Georgiev (Adobe)
END:VEVENT
END:VCALENDAR