TY - GEN
T1 - Forward and Backward Warping for Optical Flow-Based Frame Interpolation
AU - Shimizu, Joi
AU - Sun, Heming
AU - Katto, Jiro
N1 - Funding Information:
This work was supported in part by NICT, Grant Number 03801, Japan and JST, PRESTO Grant Number JPMJPR19M5, Japan. Also, we would like to thank Yuya Ishii, Masaaki Kitamoto, Tatsuhiko Furusawa, Alaric-Yohei Kawai and Ryoichi Sakamoto for helping us create the iPhone 240fps dataset.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Frame interpolation methods generate intermediate frames by taking consecutive frames as inputs. This enables the generation of high frame rate videos from low frame rate videos. Recently, many deep learning-based frame interpolation methods have been proposed. One way of frame interpolation is by using the bi-directional optical flow. In many cases, these methods use backward warping to warp the input images to the desired frame. However, forward warping can also be used to warp the input frames. In this paper, we propose a frame interpolation method that utilizes both forward warping and backward warping. Experimental results show that utilizing both warping methods can enhance the performance compared to only using backward warping.
AB - Frame interpolation methods generate intermediate frames by taking consecutive frames as inputs. This enables the generation of high frame rate videos from low frame rate videos. Recently, many deep learning-based frame interpolation methods have been proposed. One way of frame interpolation is by using the bi-directional optical flow. In many cases, these methods use backward warping to warp the input images to the desired frame. However, forward warping can also be used to warp the input frames. In this paper, we propose a frame interpolation method that utilizes both forward warping and backward warping. Experimental results show that utilizing both warping methods can enhance the performance compared to only using backward warping.
KW - deep learning
KW - frame interpolation
KW - optical flow
UR - http://www.scopus.com/inward/record.url?scp=85127714924&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85127714924&partnerID=8YFLogxK
U2 - 10.1109/ICAIIC54071.2022.9722682
DO - 10.1109/ICAIIC54071.2022.9722682
M3 - Conference contribution
AN - SCOPUS:85127714924
T3 - 4th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2022 - Proceedings
SP - 82
EP - 86
BT - 4th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2022
Y2 - 21 February 2022 through 24 February 2022
ER -