An Underwater Image Enhancement Benchmark Dataset and Beyond
This addresses the problem of inconsistent evaluation in underwater image enhancement for researchers and practitioners in marine engineering and aquatic robotics, though it is incremental as it builds on existing methods by providing a new dataset.
The authors tackled the lack of a comprehensive benchmark for evaluating underwater image enhancement algorithms by constructing a large-scale real-world dataset (UIEB) with 950 images, including 890 with reference images, and conducted a study showing the performance and limitations of state-of-the-art methods, with a proposed baseline network (Water-Net) indicating generalization for training CNNs.
Underwater image enhancement has been attracting much attention due to its significance in marine engineering and aquatic robotics. Numerous underwater image enhancement algorithms have been proposed in the last few years. However, these algorithms are mainly evaluated using either synthetic datasets or few selected real-world images. It is thus unclear how these algorithms would perform on images acquired in the wild and how we could gauge the progress in the field. To bridge this gap, we present the first comprehensive perceptual study and analysis of underwater image enhancement using large-scale real-world images. In this paper, we construct an Underwater Image Enhancement Benchmark (UIEB) including 950 real-world underwater images, 890 of which have the corresponding reference images. We treat the rest 60 underwater images which cannot obtain satisfactory reference images as challenging data. Using this dataset, we conduct a comprehensive study of the state-of-the-art underwater image enhancement algorithms qualitatively and quantitatively. In addition, we propose an underwater image enhancement network (called Water-Net) trained on this benchmark as a baseline, which indicates the generalization of the proposed UIEB for training Convolutional Neural Networks (CNNs). The benchmark evaluations and the proposed Water-Net demonstrate the performance and limitations of state-of-the-art algorithms, which shed light on future research in underwater image enhancement. The dataset and code are available at https://li-chongyi.github.io/proj_benchmark.html.