An Underwater Image Enhancement Benchmark Dataset and Beyond

Abstract:

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.

Paper:

Chongyi Li, Chunle Guo, Wenqi Ren, Runmin Cong, Junhui Hou, Sam Kwong, Dacheng Tao
An Underwater Image Enhancement Benchmark Dataset and Beyond. [arXiv version] [official version TIP 2019]

Results:

UIEB Dataset:

UIEB includes two subsets: 890 raw underwater images with corresponding high-quality reference images; 60 challenging underwater images. Please share your results on this dataset with us. We will periodically update the results for noticeable underwater image enhancement methods. The UIEBD dataset is for non-commercial use only. Please enjoy the 890 raw underwater images(~630MB) and the corresponding reference images (~786MB).
This UIEB dataset is used only for academic purposes. The re-distribution of this dataset is forbidden!!! Here is the one and only download port. The infringement will be held responsible.

[Raws][Google Drive Link] [Baidu Cloud Link]

[References][Google Drive Link] [Baidu Cloud Link]

[Challenging Set][Google Drive Link] [Baidu Cloud Link]

Passwords: Raw: 1234567; Reference: 8901234; Challenging: 5678901

C. Li, C. Guo, W. Ren, R. Cong, J. Hou, S. Kwong, D. Tao, “An Underwater Image Enhancement Benchmark Dataset and Beyond,” IEEE Trans. Image Process., vol. 29, pp.4376-4389, 2019.

We also released our PR 2019 Synthetic Underwater Image Datasets. Have fun! [Project page]

If you use this dataset, please cite the related paper. Thanks.

Water-Net Code:

[TensorFlow Code]
[PyTorch Code by Yudong Wang (yudongwang1226@gmail.com)]

TIP 2016 Code:

We released our TIP 2016 underwater image enhancement code. Have fun! [Github Link]
If you use this code, please cite the related papers. Thanks.

C. Li, J. Guo, R. Cong, et al., “Underwater image enhancement by dehazing with minimum information loss and histogram distribution prior,” IEEE Trans. Image Process., vol. 25, no. 12, pp.5664-5677, 2016.

C. Li, J. Guo, S. Chen, et al., “Underwater image restoration based on minimum information loss principle and optical properties of underwater imaging”, IEEE ICIP , pp. 1993-1997 (2016).

If you use this code and dataset, please also cite the following papers:

C. Ancuti, C. O. Ancuti, and P. Bekaert, "Enhancing underwater images and videos by fusion", in Proc. of IEEE Int. Conf. Comput. Vis. Pattern Rec. (CVPR), 2012, pp. 81-88.

C. Li, J. Guo, R. Cong, et al., “Underwater image enhancement by dehazing with minimum information loss and histogram distribution prior,” IEEE Trans. Image Process., vol. 25, no. 12, pp.5664-5677, 2016.

Y. Peng and P. Cosman, “Underwater image restoration based on image blurriness and light absorption”, IEEE Trans. Image Process., vol. 26, no. 4, pp.1579-1594, 2017.

Y. Peng, T. Cao, and P. Cosman, "Generalization of the dark channel prior for single image restoration", IEEE Trans. Image Process., vol. 27, no. 6, pp. 2856-2868, 2018.

C. Li, J. Guo, C. Guo, et al., "A hybrid method for underwater image correction", Pattern Rec. Lett., vol. 94, pp. 62-67, 2017.

A. Galdran, D. Pardo, and A. Picn, "Automatic Red-Channel underwater image restoration", J. Vis. Commu. and Image Repre., vol. 26, pp. 132-145, 2015.

X. Fu, Z. Fan, and M. Ling, "Two-step approach for single underwater image enhancement", in Symposium. of IEEE Intell. Signal Process. Commun. Syst., 2017, pp. 789-794.

X. Fu, P. Zhang, Y. Huang, et al., "A retinex-based enhancing approach for single underwater image", in Proc. of IEEE Int. Conf. Image Process. (ICIP), 2014, pp. 4572-4576.

P. Drews-Jr, E. Nascimento, S. Botelho, et al, "Underwater depth estimation and image restoration based on single images", IEEE Comput. Graph. Appl., vol. 36, no. 2, pp. 24-35, 2016.

K. He, J. Sun, and X. Tang, "Single image haze removal using dark channel prior", IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 12, pp. 2341-2353, 2011.

W. Ren, S. Liu, H. Zhang, et al., "Single image dehazing via multi-scale convolutional neural networks", in Proc. of Eur. Conf. Comput. Vis. (ECCV), 2016, pp. 154-169.

A. Ghani and N. Isa, "Underwater image quality enhancement through integrated color model with Rayleigh distribution, Appl. Soft Comput., vol. 27, pp. 219-230, 2015.

A. Ghani and N. Isa, "Enhancement of low quality underwater image through integrated global and local contrast correction, Appl. Soft Comput., vol. 37, pp. 332-344, 2015.