Multiscale Fusion Method for the Enhancement of Low-Light Underwater Images

Table 1

Quantitative comparison with the original and ours.

	Advantage	Disadvantage
Enhancement method based on multiple images [5–9]	The methods can accurately estimate the transmission or attenuation coefficient from multiple images to restore the image scene.	However, the method based on multiple images imposes restrictions on imaging conditions and has limited applicability.
Underwater image restoration method [10–19]	The methods considered the characteristics of underwater images formation and selective estimation of different wavelengths, which can effectively restore the underwater image.	However, the underwater image restoration methods [20–25] are not established in many underwater scenes. For example, bright sand in the foreground is mistaken for being close to the camera due to it has a high value in all channels.
Image enhancement method based on single image [20–25]	The image enhancement methods can significantly enhance the contrast and details of the underwater image.	Some image defogging methods based enhancement cannot fully recover the color and scene information of underwater images since the method ignores the relationship between the degradation degree of underwater images and the depth of the scene.
Underwater image dehazing method based on deep learning [26–28]	The methods can better achieve underwater image defogging with the help of recent deep learning.	The underwater images in different scenarios, light conditions and the turbidity of water have different characteristics. It is difficult to devise an underwater image dehazing method based on deep learning for the different lighting conditions of all oceans.
Enhancement method based on fusion [29–33]	The methods can maintain better exposedness in dark areas, improve overall contrast, and edge sharpness.	This method is not effective in restoring color cast in some underwater images.