对抗制
计算机科学
图像(数学)
约束(计算机辅助设计)
人工智能
计算机视觉
理论计算机科学
模式识别(心理学)
数学
几何学
作者
Haoran Wei,Qingbo Wu,Chenhao Wu,King Ngi Ngan,Hongliang Li,Fanman Meng,Heqian Qiu
标识
DOI:10.1109/tcsvt.2024.3387451
摘要
Due to the flexible training requirement and the appealing generalization ability, unpaired image dehazing has received increasing attention in coping with real-world hazy images. However, most of the existing methods rely on the loose dehazing-hazing cycle constraint, which makes it hard to eliminate poor-quality dehazing results when using a powerful hazing network in the training process. To address this issue, this paper proposes a simple yet efficient Adversarial Deformation Constraint (ADC). More specifically, we sequentially perform two operations, i.e., dehazing and deformation, on a hazy image. In the training process, the dehazing branch is desired to be deformation-unaware, which requires that the output of these two operations remains constant regardless of their performing order. Adversarially, the deformation branch tends to maximize the difference in the outputs of these two operations when their performing orders are different. Through an additive image decomposition model, we verify that the ADC could regularize the solution space to push the dehazing error towards zero. Finally, by incorporating ADC into the common dehazing-hazing cycle constraint, we significantly improve the robustness of unpaired image dehazing. Experiments on multiple benchmark hazy image databases demonstrate the superiority of ADC over many state-of-the-art image dehazing methods. The source code of the proposed ADC-Net will be released on https://github.com/whrws/ADC-Net.
科研通智能强力驱动
Strongly Powered by AbleSci AI