DCNet: Dual-Task Cycle Network for End-to-End Image Dehazing
Lists
Only you see this
Abstract
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.
BibTeX
@inproceedings{chen2021dcnet,
author = {Zhihua Chen and Yu Zhou and Ping Li and Xiaoyu Chi and Lei Ma and Bin Sheng},
title = {{DCNet: Dual-Task Cycle Network for End-to-End Image Dehazing}},
booktitle = {ICME},
year = {2021},
doi = {10.1109/icme51207.2021.9428282},
}Loading related content...