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:20240214T070243Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T172000
DTEND;TZID=Australia/Melbourne:20231212T173000
UID:siggraphasia_SIGGRAPH Asia 2023_sess142_papers_652@linklings.com
SUMMARY:Adaptive Recurrent Frame Prediction with Learnable Motion Vectors
DESCRIPTION:Technical Communications, Technical Papers\n\nZhizhen Wu (Stat
 e Key Lab of CAD&CG, Zhejiang University); Chenyu Zuo (State Key Lab of CA
 D&CG, State Key Laboratory of CAD & CG, Zhejiang University); Yuchi Huo (S
 tate Key Lab of CAD&CG, Zhejiang University; Zhejiang Lab); Yazhen Yuan (T
 encent); Yifan Peng (The University of Hong Kong (HKU)); Guiyang Pu (China
  Mobile (Hangzhou) Information Technology Co., Ltd); and Rui Wang and Huju
 n Bao (State Key Lab of CAD&CG, Zhejiang University)\n\nThe utilization of
  dedicated ray tracing graphics cards has contributed to the production of
  stunning visual effects in real-time rendering. However, the demand for h
 igh frame rates and high resolutions remains a challenge to be addressed. 
 A crucial technique for increasing frame rate and resolution is the pixel 
 warping approach, which exploits spatio-temporal coherence. \nTo this end,
  existing super-resolution and frame prediction methods rely heavily on mo
 tion vectors from rendering engine pipelines to track object movements. \n
 This work builds upon state-of-the-art heuristic approaches by exploring a
  novel adaptive recurrent frame prediction framework that integrates learn
 able motion vectors. Our framework supports the prediction of transparency
 , particles, and texture animations, with improved motion vectors that cap
 ture shading, reflections, and occlusions, in addition to geometry movemen
 ts. \nWe also introduce a feature streaming neural network, dubbed FSNet, 
 that allows for the adaptive prediction of one or multiple sequential fram
 es. Extensive experiments against state-of-the-art methods demonstrate tha
 t FSNet can operate at lower latency with significant visual enhancements 
 and can upscale frame rates by at least two times. This approach offers a 
 flexible pipeline to improve the rendering frame rates of various graphics
  applications and devices.\n\nRegistration Category: Full Access\n\nSessio
 n Chair: Michael Gharbi (Adobe, MIT)
URL:https://asia.siggraph.org/2023/full-program?id=papers_652&sess=sess142
END:VEVENT
END:VCALENDAR