BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T171535Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241205T154300
DTEND;TZID=Asia/Tokyo:20241205T155400
UID:siggraphasia_SIGGRAPH Asia 2024_sess135_papers_446@linklings.com
SUMMARY:GFFE: G-buffer Free Frame Extrapolation for Low-latency Real-time 
 Rendering
DESCRIPTION:Songyin Wu (University of California Santa Barbara); Deepak Ve
 mbar, Anton Sochenov, and Selvakumar Panneer (Intel Corporation); Sungye K
 im (Intel (now AMD)); Anton Kaplanyan (Intel Corporation); and Ling-Qi Yan
  (University of California Santa Barbara)\n\nReal-time rendering has been 
 embracing ever-demanding effects, such as ray tracing. However, rendering 
 such effects in high resolution and high frame rate remains challenging. F
 rame extrapolation methods, which do not introduce additional latency as o
 pposed to frame interpolation methods such as DLSS 3 and FSR 3, boost the 
 frame rate by generating future frames based on previous frames. However, 
 it is a more challenging task because of the lack of information in the di
 socclusion regions and complex future motions, and recent methods also hav
 e a high engine integration cost due to requiring G-buffers as input. We p
 ropose a \emph{G-buffer free} frame extrapolation method, GFFE, with a nov
 el heuristic framework and an efficient neural network, to plausibly gener
 ate new frames in real time without introducing additional latency. We ana
 lyze the motion of dynamic fragments and different types of disocclusions,
  and design the corresponding modules of the extrapolation block to handle
  them. After that, a light-weight shading correction network is used to co
 rrect shading and improve overall quality. GFFE achieves comparable or bet
 ter results than previous interpolation and G-buffer dependent extrapolati
 on methods, with more efficient performance and easier integration.\n\nReg
 istration Category: Full Access, Full Access Supporter\n\nLanguage Format:
  English Language\n\nSession Chair: Changjian Li (University of Edinburgh)
 \n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_446&sess=sess135
END:VEVENT
END:VCALENDAR