Abstract
The restoration of a corrupted image is a challenge to computer vision and image processing. In hazy, underwater and medical images, the lack of paired images lead the state of the art to synthesize datasets. The Generative Adversarial Networks (GANs) are widely used in these cases. However, computational cost and training instability are current concerns. We present an unsupervised learning algorithm that does not requires paired dataset to train encoder-decoder-like neural network for image restoration. An encoder-decoder learn to represent its input data in a latent representation and reconstruct then in the output. During the training stage, our algorithm applies the encoder-decoder output image to a degradation block that reinforces its degradation. The degraded and input images are matched using a loss function. After the training process, we obtain a restored image from the decoder. We used ill-exposed images to evaluate and validate our algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anwar, S., Barnes, N., Petersson, L.: Attention prior for real image restoration. arXiv:2004.13524v1 [cs.CV], April 2020
Bychkovsky, V., Paris, S., Chan, E., Durand, F.: Learning photographic global tonal adjustment with a database of input/output image pairs. In: IEEE CVPR, pp. 97–104, July 2011. https://doi.org/10.1109/CVPR.2011.5995413
Cai, J., Gu, S., Zhang, L.: Learning a deep single image contrast enhancer from multi-exposure images. IEEE Trans. Image Process. 1 (2018). https://doi.org/10.1109/TIP.2018.2794218
Charte, D., Charte, F., GarcÃa, S., Del Jesus, M.J., Herrera, F.: A practical tutorial on autoencoders for nonlinear feature fusion: taxonomy, models, software and guidelines. Inf. Fusion 44, 78–96 (2018). https://doi.org/10.1016/j.inffus.2017.12.007
Chen, Y., Zhang, M., Bai, M., Chen, W.: Improving the signal-to-noise ratio of seismological datasets by unsupervised machine learning. Seismol. Res. Lett. (2019). https://doi.org/10.1785/0220190028
Clevert, D.A., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUs). arXiv preprint arXiv:1511.07289 (2015)
Dong, Y., Liu, Y., Zhang, H., Chen, S., Qiao, Y.: FD-GAN: generative adversarial networks with fusion-discriminator for single image dehazing. In: AAAI, pp. 10729–10736 (2020)
Du, W., Chen, H., Yang, H.: Learning invariant representation for unsupervised image restoration. arXiv:2003.12769v1, March 2020
Fabbri, C., Islam, M.J., Sattar, J.: Enhancing underwater imagery using generative adversarial networks. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 7159–7165 (2018)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. J. Mach. Learn. Res. Proc. Track 9, 249–256 (2010)
Gonçalves, L.T., Gaya, J.F.O., Drews-Jr, P.L.J., Botelho, S.S.C.: GuidedNet: single image dehazing using an end-to-end convolutional neural network. In: Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 79–86 (2018)
Hashisho, Y., Albadawi, M., Krause, T., von Lukas, U.F.: Underwater color restoration using u-net denoising autoencoder. In: 2019 11th International Symposium on Image and Signal Processing and Analysis (ISPA), pp. 117–122 (2019)
Liu, J., Sun, Y., Eldeniz, C., Gan, W., An, H., Kamilov, U.S.: RARE: image reconstruction using deep priors learned without ground truth. IEEE J. Sel. Top. Sign. Proces. 14(6), 1–1 (2020)
Lucic, M., Kurach, K., Michalski, M., Gelly, S., Bousquet, O.: Are GANs created equal? a large-scale study. arXiv:1711.10337v4 (11 2018)
Mei, Y., et al.: Pyramid attention networks for image restoration. arXiv:2004.13824v1 [cs.CV] (04 2020)
Michelashvili, M., Wolf, L.: Audio denoising with deep network priors. arXiv:1904.07612v2, April 2019
Prakash, M., Lalit, M., Tomancak, P., Krull, A., Jug, F.: Fully unsupervised probabilistic noise2void. arXiv:1911.12291v2 [eess.IV], November 2019
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. ArXiv abs/1505.04597 (2015)
Ruiz-del-Solar, J., Loncomilla, P., Soto, N.: A survey on deep learning methods for robot vision. CoRR abs/1803.10862 (2018). http://arxiv.org/abs/1803.10862
Sharma, G., Wu, W., Dalal, E.: The ciede2000 color-difference formula: Implementation notes, supplementary test data, and mathematical observations. Color Res. Appl. 30, 21–30 (2005). https://doi.org/10.1002/col.20070
Steffens, C.R., Drews-Jr, P.L.J., Botelho, S.S.C.: Deep learning based exposure correction for image exposure correction with application in computer vision for robotics. In: 2018 Latin American Robotic Symposium, 2018 Brazilian Symposium on Robotics (SBR) and 2018 Workshop on Robotics in Education (WRE), pp. 194–200 (2018)
Steffens, C.R., Messias, L.R.V., Drews-Jr, P.L.J., Botelho, S.S.C.: Can exposure, noise and compression affect image recognition? an assessment of the impacts on state-of-the-art convnets. In: 2019 Latin American Robotics Symposium (LARS), 2019 Brazilian Symposium on Robotics (SBR) and 2019 Workshop on Robotics in Education (WRE), pp. 61–66 (2019)
Steffens, C.R., Messias, L.R.V., Drews-Jr, P.L.J., Botelho, S.S.C.: CNN based image restoration: adjusting ill-exposed srgb images in post-processing. J. Intell. Roboti. Syst. 99, 609–627 (2020)
Wang, N., Zhou, Y., Han, F., Zhu, H., Zheng, Y.: UWGAN: underwater GAN for real-world underwater color restoration and dehazing. arXiv preprint arXiv:1912.10269 (2019)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Wu, D., Gong, K., Kim, K., Li, X., Li, Q.: Consensus neural network for medical imaging denoising with only noisy training samples. arXiv:1906:03639v1 (06 2019)
Xue, W., Zhang, L., Mou, X., Bovik, A.: Gradient magnitude similarity deviation: a highly efficient perceptual image quality index. IEEE Trans. Image Process. 23 (2013). https://doi.org/10.1109/TIP.2013.2293423
Zhang, H.-M., Dong, B.: A review on deep learning in medical image reconstruction. J. Oper. Res. Soc. Chin. 8(2), 311–340 (2020). https://doi.org/10.1007/s40305-019-00287-4
Zhang, L., Zhang, L., Mou, X.: FSIM: a feature similarity index for image quality assessment. IEEE Trans. Image Process. 20, 2378–2386 (2011). https://doi.org/10.1109/TIP.2011.2109730
Zhou, Y., Wang, J., Li, B., Meng, Q., Rocco, E., Saiani, A.: Underwater scene segmentation by deep neural network. In: UK-RAS19 Conference: Embedded Intelligence: Enabling & Supporting RAS Technologies, pp. 44–47, January 2019. https://doi.org/10.31256/UKRAS19.12
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Mello, C.D., Messias, L.R.V., Drews-Jr, P.L.J., Botelho, S.S.C. (2020). Unsupervised Learning Method for Encoder-Decoder-Based Image Restoration. In: Cerri, R., Prati, R.C. (eds) Intelligent Systems. BRACIS 2020. Lecture Notes in Computer Science(), vol 12319. Springer, Cham. https://doi.org/10.1007/978-3-030-61377-8_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-61377-8_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61376-1
Online ISBN: 978-3-030-61377-8
eBook Packages: Computer ScienceComputer Science (R0)