Fig. 1. Structure of underwater image enhancement model with multiplexed fusion deep aggregate learning

Fig. 2. Loss function curves of proposed method in different training sets

Fig. 3. Treatment results of UIEB dataset images by different methods

Fig. 4. Treatment results of LSUI dataset images by different methods

Fig. 5. Comparison of image sharpness and edges by different methods on LSUI dataset

Fig. 6. Comparison of image details by different methods on UIEB dataset

Fig. 7. Effectiveness comparison of image segmentation and key point detection on UIEB dataset. (a1)‒(c1) Original images; (a2)‒(c2) segmentation images of original images; (a3)‒(c3) key point detection results of original images; (a4)‒(c4) enhanced images; (a5)‒(c5) segmentation images of enhanced images; (a6)‒(c6) key point detection results of enhanced images

Table 1. Division of different underwater datasets

Table 2. PSNR and SSIM on UIEB and LSUI datasets by different methods

Table 3. UCIQE and entropy on UIEB and LSUI datasets by different methods

Table 4. Results of ablation experiments

Table 5. Runtime and FPS of different methods