Combining Multi-level Loss for Image Denoising

The image processing has witnessed remarkable progress in image denoising. Nevertheless, restoring the visual quality of the image remains a great challenge. Existing methods might fail to obtain the denoised images with high visual quality since they ignore the potential connection with the high-level feature and result in over-smoothing results. Aiming to research whether high-level feature could influence the performance of denoising task, we propose an end-to-end multi-module neural network architecture, which introduces the combination of the high-level and low-level feature in the training process, for image denoising. In order to guide model preserve structural information efficiently, we introduce a hybrid loss, which is designed to restore details from both pixel and feature space. The experimental results show our method improves the visual quality of images and performs well compared with state-of-the-art methods on three benchmarks.

[1]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[2]  Stefan Harmeling,et al.  Image denoising: Can plain neural networks compete with BM3D? , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Luc Van Gool,et al.  The Pascal Visual Object Classes Challenge: A Retrospective , 2014, International Journal of Computer Vision.

[4]  Guillermo Sapiro,et al.  Non-local sparse models for image restoration , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[5]  Lei Zhang,et al.  Weighted Nuclear Norm Minimization with Application to Image Denoising , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

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

[7]  Yair Weiss,et al.  From learning models of natural image patches to whole image restoration , 2011, 2011 International Conference on Computer Vision.

[8]  Enhong Chen,et al.  Image Denoising and Inpainting with Deep Neural Networks , 2012, NIPS.

[9]  Thomas A. Funkhouser,et al.  Dilated Residual Networks , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[11]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[13]  M. Elad,et al.  $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation , 2006, IEEE Transactions on Signal Processing.

[14]  Alan C. Bovik,et al.  A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms , 2006, IEEE Transactions on Image Processing.

[15]  José M. Bioucas-Dias,et al.  Class-specific poisson denoising by patch-based importance sampling , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[16]  Raja Giryes,et al.  Class-Aware Fully Convolutional Gaussian and Poisson Denoising , 2018, IEEE Transactions on Image Processing.

[17]  Lei Zhang,et al.  FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising , 2017, IEEE Transactions on Image Processing.

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

[19]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[20]  Mingxuan Sun,et al.  Dilated Deep Residual Network for Image Denoising , 2017, 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI).

[21]  Stamatios Lefkimmiatis,et al.  Universal Denoising Networks : A Novel CNN Architecture for Image Denoising , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[22]  Karen O. Egiazarian,et al.  Color Image Denoising via Sparse 3D Collaborative Filtering with Grouping Constraint in Luminance-Chrominance Space , 2007, 2007 IEEE International Conference on Image Processing.

[23]  Xianming Liu,et al.  When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach , 2017, IJCAI.

[24]  Yu-Bin Yang,et al.  Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections , 2016, NIPS.

[25]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Xuanqin Mou,et al.  Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss , 2017, IEEE Transactions on Medical Imaging.

[27]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.