Illumination Controllable Dehazing Network based on Unsupervised Retinex Embedding
This addresses the need for customizable dehazing in computer vision applications, offering an incremental improvement with controllable outputs.
The paper tackles the ill-posed problem of image dehazing by proposing IC-Dehazing, a network that provides user-selectable dehazed images through illumination control, achieving competitive performance on tasks like image dehazing, semantic segmentation, and object detection without paired data.
On the one hand, the dehazing task is an illposedness problem, which means that no unique solution exists. On the other hand, the dehazing task should take into account the subjective factor, which is to give the user selectable dehazed images rather than a single result. Therefore, this paper proposes a multi-output dehazing network by introducing illumination controllable ability, called IC-Dehazing. The proposed IC-Dehazing can change the illumination intensity by adjusting the factor of the illumination controllable module, which is realized based on the interpretable Retinex theory. Moreover, the backbone dehazing network of IC-Dehazing consists of a Transformer with double decoders for high-quality image restoration. Further, the prior-based loss function and unsupervised training strategy enable IC-Dehazing to complete the parameter learning process without the need for paired data. To demonstrate the effectiveness of the proposed IC-Dehazing, quantitative and qualitative experiments are conducted on image dehazing, semantic segmentation, and object detection tasks. Code is available at https://github.com/Xiaofeng-life/ICDehazing.