GFFE: G-buffer Free Frame Extrapolation for Low-latency Real-time Rendering

被引:1
|
作者
Wu, Songyin [1 ]
Vembar, Deepak [2 ]
Sochenov, Anton [2 ]
Panneer, Selvakumar [2 ]
Kim, Sungye [3 ]
Kaplanyan, Anton [2 ]
Yan, Ling-Qi [1 ]
机构
[1] Univ Calif Santa Barbara, Santa Barbara, CA 93106 USA
[2] Intel Corp, Santa Clara, CA 10562 USA
[3] Intel Corp now AMD, Santa Clara, CA USA
来源
ACM TRANSACTIONS ON GRAPHICS | 2024年 / 43卷 / 06期
关键词
Extrapolation; Low Latency; Warping; G-buffer Free;
D O I
10.1145/3687923
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Real-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. Frame extrapolation methods, which do not introduce additional latency as opposed 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 disocclusion regions and complex future motions, and recent methods also have a high engine integration cost due to requiring G-buffers as input. We propose a G-buffer free frame extrapolation method, GFFE, with a novel heuristic framework and an efficient neural network, to plausibly generate new frames in real time without introducing additional latency. We analyze 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 correct shading and improve overall quality. GFFE achieves comparable or better results than previous interpolation and G-buffer dependent extrapolation methods, with more efficient performance and easier integration.
引用
收藏
页数:15
相关论文
共 50 条
  • [31] A Universal Optical Flow Based Real-Time Low-Latency Omnidirectional Stereo Video System
    Tang, Minhao
    Wen, Jiangtao
    Zhang, Yu
    Gu, Jiawen
    Junker, Philip
    Guo, Bichuan
    Jhao, Guansyun
    Zhu, Ziyu
    Han, Yuxing
    IEEE TRANSACTIONS ON MULTIMEDIA, 2019, 21 (04) : 957 - 972
  • [32] REAL-TIME LOW-LATENCY MUSIC SOURCE SEPARATION USING HYBRID SPECTROGRAM-TASNET
    Venkatesh, Satvik
    Benilov, Arthur
    Coleman, Philip
    Roskam, Frederic
    2024 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, ICASSP 2024, 2024, : 611 - 615
  • [33] NaNet: a flexible and configurable low-latency NIC for real-time trigger systems based on GPUs
    Ammendola, R.
    Biagioni, A.
    Frezza, O.
    Lamanna, G.
    Lonardo, A.
    Lo Cicero, F.
    Paolucci, P. S.
    Pantaleo, F.
    Rossetti, D.
    Simula, F.
    Sozzi, M.
    Tosoratto, L.
    Vicini, P.
    JOURNAL OF INSTRUMENTATION, 2014, 9
  • [34] NaNet: a low-latency NIC enabling GPU-based, real-time low level trigger systems
    Ammendola, Roberto
    Biagioni, Andrea
    Fantechi, Riccardo
    Frezza, Ottorino
    Lamanna, Gianluca
    Lo Cicero, Francesca
    Lonardo, Alessandro
    Paolucci, Pier Stanislao
    Pantaleo, Felice
    Piandani, Roberto
    Pontisso, Luca
    Rossetti, Davide
    Simula, Francesco
    Sozzi, Marco
    Tosoratto, Laura
    Vicini, Piero
    20TH INTERNATIONAL CONFERENCE ON COMPUTING IN HIGH ENERGY AND NUCLEAR PHYSICS (CHEP2013), PARTS 1-6, 2014, 513
  • [35] Dynamic Buffer Sizing and Pacing as Enablers of 5G Low-Latency Services
    Irazabal, Mikel
    Lopez-Aguilera, Elena
    Demirkol, Ilker
    Nikaein, Navid
    IEEE TRANSACTIONS ON MOBILE COMPUTING, 2022, 21 (03) : 926 - 939
  • [36] Low-latency single channel real-time neural spike sorting system based on template matching
    Wang, Pan Ke
    Pun, Sio Hang
    Chen, Chang Hao
    McCullagh, Elizabeth A.
    Klug, Achim
    Li, Anan
    Vai, Mang, I
    Mak, Peng Un
    Lei, Tim C.
    PLOS ONE, 2019, 14 (11):
  • [37] Digital filters for low-latency quantification of brain rhythms in real time
    Smetanin, Nikolai
    Belinskaya, Anastasia
    Lebedev, Mikhail
    Ossadtchi, Alexei
    JOURNAL OF NEURAL ENGINEERING, 2020, 17 (04)
  • [38] ReconSocket: a low-latency raw data streaming interface for real-time MRI-guided radiotherapy
    Borman, P. T. S.
    Raaymakers, B. W.
    Glitzner, M.
    PHYSICS IN MEDICINE AND BIOLOGY, 2019, 64 (18):
  • [39] A low-latency real-time PAM-4 receiver enabled by deep-parallel technique
    Chen, Liuyan
    Li, Chao
    Oh, Chin Wan
    Koonen, A. M. J.
    OPTICS COMMUNICATIONS, 2022, 508
  • [40] A low-latency pipeline for GRB light curve and spectrum using FermilGBM near real-time data
    Zhao, Yi
    Zhang, Bin-Bin
    Xiong, Shao-Lin
    Long, Xi
    Zhang, Qiang
    Song, Li-Ming
    Sun, Jian-Chao
    Wang, Yuan-Hao
    Li, Han-Cheng
    Bu, Qing-Cui
    Feng, Min-Zi
    Li, Zheng-Heng
    Wen, Xing
    Wu, Bo-Bing
    Zhang, Lai-Yu
    Zhang, Yong-Jie
    Zhang, Shuang-Nan
    Shao, Jian-Xiong
    RESEARCH IN ASTRONOMY AND ASTROPHYSICS, 2018, 18 (05)