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:20240214T070240Z
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_652@linklings.com
SUMMARY:Adaptive Recurrent Frame Prediction with Learnable Motion Vectors
DESCRIPTION:Technical Papers\n\nZhizhen Wu (State Key Lab of CAD&CG, Zheji
 ang University); Chenyu Zuo (State Key Lab of CAD&CG, State Key Laboratory
  of CAD & CG, Zhejiang University); Yuchi Huo (State Key Lab of CAD&CG, Zh
 ejiang University; Zhejiang Lab); Yazhen Yuan (Tencent); Yifan Peng (The U
 niversity of Hong Kong (HKU)); Guiyang Pu (China Mobile (Hangzhou) Informa
 tion Technology Co., Ltd); and Rui Wang and Hujun Bao (State Key Lab of CA
 D&CG, Zhejiang University)\n\nThe utilization of dedicated ray tracing gra
 phics cards has contributed to the production of stunning visual effects i
 n real-time rendering. However, the demand for high frame rates and high r
 esolutions remains a challenge to be addressed. A crucial technique for in
 creasing frame rate and resolution is the pixel warping approach, which ex
 ploits spatio-temporal coherence. \nTo this end, existing super-resolution
  and frame prediction methods rely heavily on motion vectors from renderin
 g engine pipelines to track object movements. \nThis work builds upon stat
 e-of-the-art heuristic approaches by exploring a novel adaptive recurrent 
 frame prediction framework that integrates learnable motion vectors. Our f
 ramework supports the prediction of transparency, particles, and texture a
 nimations, with improved motion vectors that capture shading, reflections,
  and occlusions, in addition to geometry movements. \nWe also introduce a 
 feature streaming neural network, dubbed FSNet, that allows for the adapti
 ve prediction of one or multiple sequential frames. Extensive experiments 
 against state-of-the-art methods demonstrate that FSNet can operate at low
 er latency with significant visual enhancements and can upscale frame rate
 s by at least two times. This approach offers a flexible pipeline to impro
 ve the rendering frame rates of various graphics applications and devices.
 \n\nRegistration Category: Full Access, Enhanced Access, Trade Exhibitor, 
 Experience Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=papers_652&sess=sess209
END:VEVENT
END:VCALENDAR