TY - GEN
T1 - Video Generation and Synthesis Network for Long-term Video Interpolation
AU - Kim, Nayoung
AU - Lee, Jung Kyung
AU - Yoo, Chae Hwa
AU - Cho, Seunghyun
AU - Kang, Je Won
N1 - Funding Information:
This work was supported by Institute for Information and communications Technology Promotion(IITP) grant funded by the Korea government(MSIP) (2017-0-00072, Development of Audio/Video Coding and Light Field Media Fundamental Technologies for Ultra Realistic Tera-media and the Basic Science Research Program through the National Research Foundation of Korea (NRF)(NRF-2016R1D1A1B03932994).)
Publisher Copyright:
© 2018 APSIPA organization.
PY - 2019/3/4
Y1 - 2019/3/4
N2 - In this paper, we propose a bidirectional synthesis video interpolation technique based on deep learning, using a forward and a backward video generation network and a synthesis network. The forward generation network first extrapolates a video sequence, given the past video frames, and then the backward generation network generates the same video sequence, given the future video frames. Next, a synthesis network fuses the results of the two generation networks to create an intermediate video sequence. To jointly train the video generation and synthesis networks, we define a cost function to approximate the visual quality and the motion of the interpolated video as close as possible to those of the original video. Experimental results show that the proposed technique outperforms the state-of-the art long-term video interpolation model based on deep learning.
AB - In this paper, we propose a bidirectional synthesis video interpolation technique based on deep learning, using a forward and a backward video generation network and a synthesis network. The forward generation network first extrapolates a video sequence, given the past video frames, and then the backward generation network generates the same video sequence, given the future video frames. Next, a synthesis network fuses the results of the two generation networks to create an intermediate video sequence. To jointly train the video generation and synthesis networks, we define a cost function to approximate the visual quality and the motion of the interpolated video as close as possible to those of the original video. Experimental results show that the proposed technique outperforms the state-of-the art long-term video interpolation model based on deep learning.
UR - http://www.scopus.com/inward/record.url?scp=85063461549&partnerID=8YFLogxK
U2 - 10.23919/APSIPA.2018.8659743
DO - 10.23919/APSIPA.2018.8659743
M3 - Conference contribution
AN - SCOPUS:85063461549
T3 - 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings
SP - 705
EP - 709
BT - 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 12 November 2018 through 15 November 2018
ER -