Single Underwater Image Enhancement Based on Transmission Map Weighted Fusion and Adaptive Color Correction
Xu-Dong Tang, Yajuan Wu · 2023
The complex underwater environment and the absorption and scattering of light in the water lead to color degradation and loss of detail during the underwater imaging process. To address these problems, we propose a single-shot underwater image enhancement method based on the transfer graph normalization weighted fusion method and adaptive color correction, using a weighted fusion technique to combine the improved transfer graph with a bilateral filtering algorithm, which aims to defog underwater images and improve their contrast. Furthermore, by calculating the relative standard deviation between the three color channels, a novel adaptive correction method is designed to solve the image distortion problem due to light propagation underwater. Experimental results show that this comprehensive method performs well in underwater image enhancement.