DENSECL: HAZE MITIGATION USING DENSE BLOCKS AND CONTRASTIVE LOSS REGULARIZATION

Haze, which occurs as a result of the scattering of light in the atmosphere by small particles, diminishes the visibility of the scene, inflicting important image applications such as object detection. To address the problem, this paper introduces a new physics-based end-to-end deep learning approach to haze mitigation in outdoor scenes, including airborne images. The proposed model named DenseCL is designed by learning features to capture and de-haze pixels through dense blocks by enforcing contrastive loss regularization. The model also maintains cycle consistency by remapping the dehazed outputs into a hazy image using the physics-based light scattering function. DenseCL has been trained with publicly available outdoor images and demonstrates outstanding performance on outdoor, indoor and remotely sensed non-homogeneous haze satellite images.