UW-GAN: Single-Image Depth Estimation and Image Enhancement for Underwater Images

• Published in: IEEE transactions on instrumentation and measurement Vol. 70; pp. 1 - 12
• Main Authors: Hambarde, Praful, Murala, Subrahmanyam, Dhall, Abhinav
• Format: Journal Article
• Language: English
• Published: New York IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adversarial learning; coarse-level depth; Datasets; Deep learning; Estimation; fine-level depth; Generative adversarial networks; Ill posed problems; Image color analysis; Image contrast; Image enhancement; Image processing; Image restoration; Marine engineering; Robotics; Task analysis; underwater depth estimation; Underwater robots
• ISSN: 0018-9456; 1557-9662
• DOI: 10.1109/TIM.2021.3120130

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 end-to-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 large-scale 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.