“…Besides this, some researchers used the conventional methods: Gray World [41], Shades of Grey [42], Gray-Edge [43], max-RGB [44], [45] and Color Equalization [46] for removal of color casts in addition to restoration. The advancement of Deep Learning also provides a considerable contribution to underwater image enhancement, which include Deep residual net [47], Feedback Adversarial Transfer Learning [48], structure decomposition network [49], multiscale dense GAN [50], channel wise feature map based residual block [51], JLCL-Net [52], Feature Fusion Network [53], UW-GAN [54], TOPAL [55], DPIENet [56], SCEIR [57], SGUIE-Net [58], UAGAN [59], Fusion of features of RGB and HSV spaces by MSDC-Net [60], designing of neural network using physical model of [6] and [7] by HybrUR [61], adaptive DLN with dewater pooling and new attention mechanism [62], U-shape transformer was integrated with the combination of channel-wise and global-wise modelling transformer [63]. Underwater image curve model was proposed based on model of haze image for the enhancement of degraded images without any reference images (Zero-UIE) [64] where lightweight deep network was used for the estimation of curve parameters.…”