Multi-level Wavelet-CNN for Image Restoration
Pengju Liu,Hongzhi Zhang,Kai Zhang,Liang Lin,Wangmeng Zuo +4 more
- pp 773-782
TLDR
In this article, a multi-level wavelet CNN (MWCNN) model is proposed for image denoising, single image super-resolution, and JPEG image artifacts removal, which can be applied to many image restoration tasks.Abstract:
The tradeoff between receptive field size and efficiency is a crucial issue in low level vision. Plain convolutional networks (CNNs) generally enlarge the receptive field at the expense of computational cost. Recently, dilated filtering has been adopted to address this issue. But it suffers from gridding effect, and the resulting receptive field is only a sparse sampling of input image with checkerboard patterns. In this paper, we present a novel multi-level wavelet CNN (MWCNN) model for better tradeoff between receptive field size and computational efficiency. With the modified U-Net architecture, wavelet transform is introduced to reduce the size of feature maps in the contracting subnetwork. Furthermore, another convolutional layer is further used to decrease the channels of feature maps. In the expanding subnetwork, inverse wavelet transform is then deployed to reconstruct the high resolution feature maps. Our MWCNN can also be explained as the generalization of dilated filtering and subsampling, and can be applied to many image restoration tasks. The experimental results clearly show the effectiveness of MWCNN for image denoising, single image super-resolution, and JPEG image artifacts removal.read more
Citations
More filters
Journal ArticleDOI
Deep Learning for Image Super-Resolution: A Survey
TL;DR: A survey on recent advances of image super-resolution techniques using deep learning approaches in a systematic way, which can roughly group the existing studies of SR techniques into three major categories: supervised SR, unsupervised SR, and domain-specific SR.
Proceedings ArticleDOI
Toward Convolutional Blind Denoising of Real Photographs
TL;DR: CBDNet as discussed by the authors proposes to train a convolutional blind denoising network with more realistic noise model and real-world clean image pairs to improve the generalization ability of deep CNN denoisers.
Journal ArticleDOI
Residual Dense Network for Image Restoration
TL;DR: Zhang et al. as mentioned in this paper proposed a residual dense block (RDB) to extract abundant local features via densely connected convolutional layers, which further allows direct connections from the state of preceding RDB to all the layers of current RDB, leading to a contiguous memory mechanism.
Proceedings ArticleDOI
FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation
TL;DR: A state-of-the-art video denoising algorithm based on a convolutional neural network architecture that exhibits several desirable properties such as fast runtimes, and the ability to handle a wide range of noise levels with a single network model.
Proceedings ArticleDOI
Self-Guided Network for Fast Image Denoising
TL;DR: A self-guided network (SGN), which adopts a top-down self-guidance architecture to better exploit image multi-scale information and extract good local features to recover noisy images.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Book ChapterDOI
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Proceedings Article
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.
Journal ArticleDOI
A theory for multiresolution signal decomposition: the wavelet representation
TL;DR: In this paper, it is shown that the difference of information between the approximation of a signal at the resolutions 2/sup j+1/ and 2 /sup j/ (where j is an integer) can be extracted by decomposing this signal on a wavelet orthonormal basis of L/sup 2/(R/sup n/), the vector space of measurable, square-integrable n-dimensional functions.