Progressive Training of Multi-level Wavelet Residual Networks for Image Denoising

Recent years have witnessed the great success of deep convolutional neural networks (CNNs) in image denoising. Albeit deeper network and larger model capacity generally benefit performance, it remains a challenging practical issue to train a very deep image denoising network. Using multilevel wavelet-CNN (MWCNN) as an example, we empirically find that the denoising performance cannot be significantly improved by either increasing wavelet decomposition levels or increasing convolution layers within each level. To cope with this issue, this paper presents a multi-level wavelet residual network (MWRN) architecture as well as a progressive training (PTMWRN) scheme to improve image denoising performance. In contrast to MWCNN, our MWRN introduces several residual blocks after each level of discrete wavelet transform (DWT) and before inverse discrete wavelet transform (IDWT). For easing the training difficulty, scale-specific loss is applied to each level of MWRN by requiring the intermediate output to approximate the corresponding wavelet subbands of ground-truth clean image. To ensure the effectiveness of scale-specific loss, we also take the wavelet subbands of noisy image as the input to each scale of the encoder. Furthermore, progressive training scheme is adopted for better learning of MWRN by beigining with training the lowest level of MWRN and progressively training the upper levels to bring more fine details to denoising results. Experiments on both synthetic and real-world noisy images show that our PT-MWRN performs favorably against the state-of-the-art denoising methods in terms both quantitative metrics and visual quality.

[1]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Jitendra Malik,et al.  A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[3]  Stephen Lin,et al.  A High-Quality Denoising Dataset for Smartphone Cameras , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[4]  Stamatios Lefkimmiatis,et al.  Non-local Color Image Denoising with Convolutional Neural Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Jonathan T. Barron,et al.  Unprocessing Images for Learned Raw Denoising , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Lei Zhang,et al.  Weighted Nuclear Norm Minimization and Its Applications to Low Level Vision , 2016, International Journal of Computer Vision.

[7]  Florian Jug,et al.  Noise2Void - Learning Denoising From Single Noisy Images , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Xiaoou Tang,et al.  Path-Restore: Learning Network Path Selection for Image Restoration , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Vishal Monga,et al.  Deep Wavelet Prediction for Image Super-Resolution , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

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

[11]  Stefan Roth,et al.  Benchmarking Denoising Algorithms with Real Photographs , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[13]  Stéphane Mallat,et al.  Wavelets for a vision , 1996, Proc. IEEE.

[14]  Nick Barnes,et al.  Real Image Denoising With Feature Attention , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[15]  Narendra Ahuja,et al.  Single image super-resolution from transformed self-exemplars , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Lei Zhang,et al.  Color demosaicking by local directional interpolation and nonlocal adaptive thresholding , 2011, J. Electronic Imaging.

[17]  David Zhang,et al.  Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[18]  Roberto Manduchi,et al.  Bilateral filtering for gray and color images , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[19]  Jong Chul Ye,et al.  Beyond Deep Residual Learning for Image Restoration: Persistent Homology-Guided Manifold Simplification , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[20]  Jiaolong Yang,et al.  A Physics-Based Noise Formation Model for Extreme Low-Light Raw Denoising , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  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.

[22]  Dong-Wook Kim,et al.  NTIRE 2019 Challenge on Real Image Denoising: Methods and Results , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[23]  Wangmeng Zuo,et al.  Learning Deep CNN Denoiser Prior for Image Restoration , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Dongwei Ren,et al.  Unpaired Learning of Deep Image Denoising , 2020, ECCV.

[25]  Fahad Shahbaz Khan,et al.  CycleISP: Real Image Restoration via Improved Data Synthesis , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Abhinav Gupta,et al.  Non-local Neural Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[27]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[28]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.

[29]  Jechang Jeong,et al.  Densely Connected Hierarchical Network for Image Denoising , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[30]  David Zhang,et al.  A Trilateral Weighted Sparse Coding Scheme for Real-World Image Denoising , 2018, ECCV.

[31]  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).

[32]  Stefan Roth,et al.  Neural Nearest Neighbors Networks , 2018, NeurIPS.

[33]  Wangmeng Zuo,et al.  Toward Convolutional Blind Denoising of Real Photographs , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Zhuowen Tu,et al.  Deeply-Supervised Nets , 2014, AISTATS.

[35]  Kyoung Mu Lee,et al.  Enhanced Deep Residual Networks for Single Image Super-Resolution , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[36]  Jaakko Lehtinen,et al.  High-Quality Self-Supervised Deep Image Denoising , 2019, NeurIPS.

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

[38]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[39]  A. Bruckstein,et al.  K-SVD : An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation , 2005 .

[40]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[41]  Michael S. Brown,et al.  Noise Flow: Noise Modeling With Conditional Normalizing Flows , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[42]  Karen O. Egiazarian,et al.  Image restoration by sparse 3D transform-domain collaborative filtering , 2008, Electronic Imaging.

[43]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[44]  Tieniu Tan,et al.  Wavelet-SRNet: A Wavelet-Based CNN for Multi-scale Face Super Resolution , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[45]  Aidong Men,et al.  Pyramid Real Image Denoising Network , 2019, 2019 IEEE Visual Communications and Image Processing (VCIP).

[46]  Thomas S. Huang,et al.  Non-Local Recurrent Network for Image Restoration , 2018, NeurIPS.

[47]  Jian Yang,et al.  MemNet: A Persistent Memory Network for Image Restoration , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[48]  Yoonsik Kim,et al.  Transfer Learning From Synthetic to Real-Noise Denoising With Adaptive Instance Normalization , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[49]  Deyu Meng,et al.  Variational Denoising Network: Toward Blind Noise Modeling and Removal , 2019, NeurIPS.

[50]  Lei Zhang,et al.  Waterloo Exploration Database: New Challenges for Image Quality Assessment Models , 2017, IEEE Transactions on Image Processing.

[51]  Eirikur Agustsson,et al.  NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[52]  Jechang Jeong,et al.  Deep Iterative Down-Up CNN for Image Denoising , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[53]  Michael Elad,et al.  Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries , 2006, IEEE Transactions on Image Processing.

[54]  Michael J. Black,et al.  Fields of Experts: a framework for learning image priors , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[55]  Mai Xu,et al.  Wavelet Domain Style Transfer for an Effective Perception-Distortion Tradeoff in Single Image Super-Resolution , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

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

[57]  Stefan Roth,et al.  Shrinkage Fields for Effective Image Restoration , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

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

[59]  Yun Fu,et al.  Residual Dense Network for Image Super-Resolution , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[60]  Dong-Wook Kim,et al.  GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-Based Real-World Noise Modeling , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

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

[62]  In-So Kweon,et al.  CBAM: Convolutional Block Attention Module , 2018, ECCV.