Underwater Image Enhancement Using a Multiscale Dense Generative Adversarial Network

By Ye-cai Guo, Hanyu Li, Peixian Zhuang. IEEE Journal of Oceanic Engineering, 2020

434 citations recorded by the source corpus.

Underwater image enhancement has received much attention in underwater vision research. However, raw underwater images easily suffer from color distortion, underexposure, and fuzz caused by the underwater scene. To address the above-mentioned problems, we propose a new multiscale dense generative adversarial network (GAN) for enhancing underwater images. The residual multiscale dense block is presented in the generator, where the multiscale, dense concatenation, and residual learning can boost the performance, render more details, and utilize previous features, respectively. And the discriminator employs computationally light spectral normalization to stabilize the training of the discriminator. Meanwhile, nonsaturating GAN loss function combining $L_1$ loss and gradient loss is presented to focus on image features of ground truth. Final enhanced results on synthetic and real underwater images demonstrate the superiority of the proposed method, which outperforms nondeep and deep learning methods in both qualitative and quantitative evaluations. Furthermore, we perform an ablation study to show the contributions of each component and carry out application tests to further demonstrate the effectiveness of the proposed method.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/3bf2147008e0bcb5d80298448fc4bf7f5d3c30ea

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Chongyi Li
2. Chunle Guo
3. Chunli Zhu
4. Liheng Bian
5. Lintao Peng
6. Runmin Cong
7. Junaed Sattar
8. Sam Kwong

Citations in the corpus

• U-Shape Transformer for Underwater Image Enhancement (2021, methodology): “More recently, as to the data-driven methods [21], [3], [22], [23], [24], [25], [26], [27], [28], [29], [30], [31], [4], which could be regarded as deep learning technologies in UIE domain, exhibit impressive performance on UIE task.”
• Fast Underwater Image Enhancement for Improved Visual Perception (2019, background): “ation [10], scattering, and other optical properties of the waterbodies cause irregular non-linear distortions [5], [11] which”
• UIEC^2-Net: CNN-based Underwater Image Enhancement Using Two Color Space (2021, methodology): “…modular or block has the same structure and are repeatedly applied in the network to improve the feature extraction capability of the network [25], [26]; designed multiple branch aims to learn different features through separate branches [1], [27], [28]; improving the performance of enhancement…”
• An Underwater Image Enhancement Benchmark Dataset and Beyond (2019, background): “From left to right are raw underwater images, and the results of fusion-based [31], retinex-based [33], histogram prior [45], blurriness-based [46], GDCP [40], Water CycleGAN [53], Dense GAN [55], the proposed Water-Net, and reference images.”
• Using labeled data to evaluate change detectors in a multivariate streaming environment (2009, neutral): “In the training process Adam optimizer is utilized to optimize the model.”
• Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding (2021, methodology): “[17], and UWCNN typeII [12].”