Simple Zero-Shot Image Dehazing

We present an image dehazing algorithm that leverages zero-shot learning principles and layer disentanglement techniques, surpassing the performance of existing models. Our method uniquely operates on a single hazy image for both learning and inference, eliminating the need for extensive training datasets. The optimization process of the proposed architecture is guided by a classical physical scattering model and by information extracted from the input hazy image itself. This approach ensures that the dehazed output maintains color fidelity and remains artifact-free. Such quality preservation is particularly noteworthy, as other learning-based methods often struggle with color distortions and artifacts when applied to real-world hazy images due to the domain-shift problem.