TY - GEN
T1 - DCNet: Dual-task cycle network for end-to-end image dehazing
AU - Chen, Zhihua
AU - Zhou, Yu
AU - Li, Ping
AU - Chi, Xiaoyu
AU - Ma, Lei
AU - Sheng, Bin
N1 - Funding Information:
This work was supported in part by the National Natural Science Foundation of China under Grant 61672228, Grant 61902126, Grant 61872241, and Grant 61572316, and in part by The Hong Kong Polytechnic University under Grant P0030419, Grant P0030929, and Grant P0035358.
Publisher Copyright:
© 2021 IEEE Computer Society. All rights reserved.
PY - 2021/7
Y1 - 2021/7
N2 - Single image dehazing is an important technology in the field of computer vision. In this paper, we propose an image dehazing via dual learning strategy, named dual-task cycle network (DCNet). The core of DCNet is a dual learning framework, which consists of two tasks: the dehazing task and the haze generation task. The dehazing task completes the image dehazing, while the haze generation task achieves the restoration from the dehazed image to the haze image and can form a cycle to provide additional supervision. Our method uses the duality between each task as a constraint to learn and train two tasks jointly, so that the effects of the dehazing model can be improved. Since the haze generation process does not depend on clear images, the DCNet can satisfy the requirements for limited supervision. Extensive experiments demonstrate that our DCNet performs favorably on haze removal.
AB - Single image dehazing is an important technology in the field of computer vision. In this paper, we propose an image dehazing via dual learning strategy, named dual-task cycle network (DCNet). The core of DCNet is a dual learning framework, which consists of two tasks: the dehazing task and the haze generation task. The dehazing task completes the image dehazing, while the haze generation task achieves the restoration from the dehazed image to the haze image and can form a cycle to provide additional supervision. Our method uses the duality between each task as a constraint to learn and train two tasks jointly, so that the effects of the dehazing model can be improved. Since the haze generation process does not depend on clear images, the DCNet can satisfy the requirements for limited supervision. Extensive experiments demonstrate that our DCNet performs favorably on haze removal.
KW - convolutional neural network
KW - dual learning strategy
KW - Image dehazing
UR - http://www.scopus.com/inward/record.url?scp=85126453878&partnerID=8YFLogxK
U2 - 10.1109/ICME51207.2021.9428282
DO - 10.1109/ICME51207.2021.9428282
M3 - Conference article published in proceeding or book
AN - SCOPUS:85126453878
T3 - Proceedings - IEEE International Conference on Multimedia and Expo
SP - 1
EP - 6
BT - 2021 IEEE International Conference on Multimedia and Expo, ICME 2021
PB - IEEE Computer Society
T2 - 2021 IEEE International Conference on Multimedia and Expo, ICME 2021
Y2 - 5 July 2021 through 9 July 2021
ER -