Abstract:
Due to the unavailability of large-scale underwater depth image datasets and ill-posed problems, underwater single-image depth prediction is a challenging task.
An unambiguous depth prediction for single underwater image
is an essential part of applications like underwater robotics,
marine engineering, and so on. This article presents an endto-end underwater generative adversarial network (UW-GAN)
for depth estimation from an underwater single image. Initially,
a coarse-level depth map is estimated using the underwater
coarse-level generative network (UWC-Net). Then, a fine-level
depth map is computed using the underwater fine-level network
(UWF-Net) which takes input as the concatenation of the estimated coarse-level depth map and the input image. The proposed
UWF-Net composes of spatial and channel-wise squeeze and
excitation block for fine-level depth estimation. Also, we propose
a synthetic underwater image generation approach for largescale database. The proposed network is tested on real-world
and synthetic underwater datasets for its performance analysis.
We also perform a complete evaluation of the proposed UW-GAN
on underwater images having different color domination, contrast, and lighting conditions. Presented UW-GAN framework
is also investigated for underwater single-image enhancement.
Extensive result analysis proves the superiority of proposed
UW-GAN over the state-of-the-art (SoTA) hand-crafted, and
learning-based approaches for underwater single-image depth
estimation (USIDE) and enhancement.
