Deep Learning-Enabled Variational Optimization Method for Image Dehazing in Maritime Intelligent Transportation Systems
Figure 7
Visual comparisons of synthetic experiments on six images with transmission value = 0.3 and atmospheric light value = 0.8. From left to right: (a) synthetic haze image and dehazed images generated by (b) DCP [23], (c) RIVD [30], (d) MSCNN [12], (e) ours, and (f) original clear images, respectively.
