TY - GEN
T1 - Edge Guided Generation Network for Video Prediction
AU - Xu, Kai
AU - Li, Guorong
AU - Xu, Huijuan
AU - Zhang, Weigang
AU - Huang, Qingming
N1 - Funding Information:
proach outperforms the existing state-of-the-art methods in long-term video prediction. 6. ACKNOWLEDGMENT This work was supported in part by National Natural Science Foundation of China: 61772494, 61332016, 61620106009, U1636214, 61650202 and 61672497, in part by Youth Innovation Promotion Association CAS, in part by Key Research Program of Frontier Sciences, CAS: QYZDJ-SSW-SYS013, in part by Shandong Provincial Natural Science Foundation, China: ZR2017MF001. References
Publisher Copyright:
© 2018 IEEE.
PY - 2018/10/8
Y1 - 2018/10/8
N2 - Video prediction is a challenging problem due to the highly complex variation of video appearance and motions. Traditional methods that directly predict pixel values often result in blurring and artifacts. Furthermore, cumulative errors can lead to a sharp drop of prediction quality in long-term prediction. To alleviate the above problems, we propose a novel edge guided video prediction network, which firstly models the dynamic of frame edges and predicts the future frame edges, then generates the future frames under the guidance of the obtained future frame edges. Specifically, our network consists of two modules that are ConvLSTM based edge prediction module and the edge guided frames generation module. The whole network is differentiable and can be trained end-to-end without any supervision effort. Extensive experiments on KTH human action dataset and challenging autonomous driving KITTI dataset demonstrate that our method achieves better results than state-of-the-art methods especially in long-term video predictions.
AB - Video prediction is a challenging problem due to the highly complex variation of video appearance and motions. Traditional methods that directly predict pixel values often result in blurring and artifacts. Furthermore, cumulative errors can lead to a sharp drop of prediction quality in long-term prediction. To alleviate the above problems, we propose a novel edge guided video prediction network, which firstly models the dynamic of frame edges and predicts the future frame edges, then generates the future frames under the guidance of the obtained future frame edges. Specifically, our network consists of two modules that are ConvLSTM based edge prediction module and the edge guided frames generation module. The whole network is differentiable and can be trained end-to-end without any supervision effort. Extensive experiments on KTH human action dataset and challenging autonomous driving KITTI dataset demonstrate that our method achieves better results than state-of-the-art methods especially in long-term video predictions.
UR - http://www.scopus.com/inward/record.url?scp=85061432089&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85061432089&partnerID=8YFLogxK
U2 - 10.1109/ICME.2018.8486602
DO - 10.1109/ICME.2018.8486602
M3 - Conference contribution
AN - SCOPUS:85061432089
T3 - Proceedings - IEEE International Conference on Multimedia and Expo
BT - 2018 IEEE International Conference on Multimedia and Expo, ICME 2018
PB - IEEE Computer Society
T2 - 2018 IEEE International Conference on Multimedia and Expo, ICME 2018
Y2 - 23 July 2018 through 27 July 2018
ER -