Image denoising using deep convolutional autoencoder with feature pyramids

Image denoising is 1 of the fundamental problems in the image processing field since it is the preliminary step for many computer vision applications. Various approaches have been used for image denoising throughout the years from spatial filtering to model-based approaches. Having outperformed all traditional methods, neural-network-based discriminative methods have gained popularity in recent years. However, most of these methods still struggle to achieve flexibility against various noise levels and types. In this paper, a deep convolutional autoencoder combined with a variant of feature pyramid network is proposed for image denoising. Simulated data generated by Blender software along with corrupted natural images are used during training to improve robustness against various noise levels. Experimental results show that the proposed method can achieve competitive performance in blind Gaussian denoising with significantly less training time required compared to state of the art methods. Extensive experiments showed the proposed method gives promising performance in a wide range of noise levels with a single network.

PDF

___

[1] Goldman LW. Principles of CT: radiation dose and image quality. Journal of Nuclear Medicine Technology 2007; 1; 35 (4): 213-225.
[2] Huda W. Dose and image quality in CT. Pediatric Radiology 2002; 1; 32 (10): 709.
[3] Dabov K, Foi A, Katkovnik V, Egiazarian K. Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Transactions on Image Processing 2007; 16; 16 (8): 2080-2095.
[4] Zhang K, Zuo W, Chen Y, Meng D, Zhang L. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE Transactions on Image Processing 2017; 1; 26 (7): 3142-3155.
[5] Zhang K, Zuo W, Zhang L. FFDNet: Toward a fast and flexible solution for CNN-based image denoising. IEEE Transactions on Image Processing 2018; 25; 27 (9): 4608-4622.
[6] Wang T, Sun M, Hu K. Dilated deep residual network for image denoising. In: 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI); Boston, MA, USA; 2017. pp. 1272-1279.
[7] Gu S, Zhang L, Zuo W, Feng X. Weighted nuclear norm minimization with application to image denoising. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Columbus, OH, USA; 2014. pp. 2862-2869.
[8] Chen Y, Pock T. Trainable nonlinear reaction diffusion: a flexible framework for fast and effective image restoration. IEEE Transactions on Pattern Analysis and Machine Intelligence 2016; 39 (6): 1256-1272.
[9] Burger HC, Schuler CJ, Harmeling S. Image denoising: can plain neural networks compete with BM3D? In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Providence, RI, USA; 2012. pp. 2392-2399.
[10] Jain V, Seung S. Natural image denoising with convolutional networks. In: Advances in Neural Information Processing systems (NIPS); Vancouver, B.C., Canada; 2009. pp. 769-776.
[11] Xie J, Xu L, Chen E. Image denoising and inpainting with deep neural networks. In: Advances in Neural Information Processing Systems (NIPS); Lake Tahoe, NV, USA; 2012. pp. 341-349
[12] Gondara L. Medical image denoising using convolutional denoising autoencoders. In: 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW); Barcelona, Spain; 2016. pp. 241-246.
[13] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Las Vegas, NV, USA; 2016. pp. 770-778.
[14] Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167. 2015.
[15] Guo S, Yan Z, Zhang K, Zuo W, Zhang L. Toward convolutional blind denoising of real photographs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Long Beach, CA, USA; 2019. pp. 1712-1722.
[16] Lin TY, Dollár P, Girshick R, He K, Hariharan B et al. Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Honolulu, HI, USA; 2017. pp. 2117-2125.
[17] Vincent P, Larochelle H, Lajoie I, Bengio Y, Manzagol PA. Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research 2010; 11: 3371-3408.
[18] Wang Z, Bovik AC, Sheikh HR, Simoncelli EP. Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing 2004; 13 (4): 600-12.
[19] Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D et al. Generative adversarial nets. In: Advances in Neural Information Processing Systems (NIPS); Montreal, QC, Canada; 2014. pp. 2672-2680.
[20] Tripathi S, Lipton ZC, Nguyen TQ. Correction by projection: denoising images with generative adversarial networks. arXiv preprint arXiv:1803.04477. 2018.
[21] Nair V, Hinton GE. Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML); Haifa, Israel; 2010. pp. 807-814.
[22] Kingma DP, Ba J. Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980. 2014.
[23] Arbelaez P, Maire M, Fowlkes C, Malik J. Contour detection and hierarchical image segmentation. IEEE Transac- tions on Pattern Analysis and Machine Intelligence 2010; 33 (5): 898-916.
[24] Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B et al. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research 2011; 12: 2825-2830.
[25] Paszke A, Gross S, Chintala S, Chanan G, Yang E et al. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In: Advances in Neural Information Processing Systems (NeurIPS); Vancouver, VN, Canada; 2019. pp. 8024-8035.
[26] Liu P, Zhang H, Zhang K, Lin L, Zuo W. Multi-level wavelet-CNN for image restoration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW); Salt Lake City, UT, USA; 2018. pp. 773-782.