Estimation of signal-dependent noise level function using multi-column convolutional neural network

To estimate the levels of signal-dependent noise (SDN) from a single image is challenging. This paper proposes a novel method to estimate the noise level function (NLF) from a single image using a Multi-column Convolutional Neural Network (MC-Net) with an end-to-end architecture. The MC-Net is trained on a synthesized dataset containing noisy images with known NLFs, and it allows to learn rich hierarchical features using three sub-networks. Moreover, this method performs end-to-end training to retain more details for pixel-wise noise level estimation. Experimental results indicate that our method is accurate and robust to estimate NLFs of SDN for various types of images.

[1]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[2]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[3]  Chengjin Zhang,et al.  Denoising Convolutional Neural Network , 2015, 2015 IEEE International Conference on Information and Automation.

[4]  Yunjin Chen,et al.  Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Vladimir V. Lukin,et al.  Local Signal-Dependent Noise Variance Estimation From Hyperspectral Textural Images , 2011, IEEE Journal of Selected Topics in Signal Processing.

[6]  Richard Szeliski,et al.  Automatic Estimation and Removal of Noise from a Single Image , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Lei Zhang,et al.  Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising , 2016, IEEE Transactions on Image Processing.

[9]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[10]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[11]  Xinhao Liu,et al.  Estimation of signal dependent noise parameters from a single image , 2013, 2013 IEEE International Conference on Image Processing.

[12]  Jian Sun,et al.  Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Yasuyuki Matsushita,et al.  A Holistic Approach to Cross-Channel Image Noise Modeling and Its Application to Image Denoising , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  H. Sebastian Seung,et al.  Natural Image Denoising with Convolutional Networks , 2008, NIPS.

[15]  M. Vehvilainen,et al.  New method for noise estimation in images , 2005 .

[16]  Xiaoou Tang,et al.  Learning a Deep Convolutional Network for Image Super-Resolution , 2014, ECCV.

[17]  Mohammed Ghazal,et al.  Homogeneity Localization Using Particle Filters With Application to Noise Estimation , 2011, IEEE Transactions on Image Processing.

[18]  Xiaohui Yuan,et al.  Subband noise estimation for adaptive wavelet shrinkage , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[19]  Jing-Yu Yang,et al.  Estimation of Signal-Dependent Noise Level Function in Transform Domain via a Sparse Recovery Model , 2015, IEEE Transactions on Image Processing.

[20]  Xiaoou Tang,et al.  Accelerating the Super-Resolution Convolutional Neural Network , 2016, ECCV.

[21]  Takeo Kanade,et al.  Statistical calibration of CCD imaging process , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.