Coarse-to-fine underwater image enhancement with lightweight CNN and attention-based refinement

This paper presents a deep learning-based underwater image enhancement method supported by a classical image processing technique. The proposed method includes an end-to-end three-module structure. The first module is a lightweight two-branch network that retrieves lost colors and to some extent overall appearance through the global and local image enhancement. The second module is the modified histogram equalization to improve the global intensity, contrast and local colors of the image by controlling over-intensity and artificial colors that may result from histogram equalization. The last part is the attention module, utilized to help the proposed framework have a synergistic combination of the previous modules. The attention module is designed to combine the advantages of the previous modules and evade their drawbacks. Experiments to objectively and subjectively evaluate the performance of the proposed model show that the proposed model is superior to existing underwater image enhancement methods.