Self-tuned deep super resolution

@article{Wang2015SelftunedDS,
  title={Self-tuned deep super resolution},
  author={Zhangyang Wang and Yingzhen Yang and Zhaowen Wang and Shiyu Chang and Wei Han and Jianchao Yang and Thomas S. Huang},
  journal={2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2015},
  pages={1-8}
}
Deep learning has been successfully applied to image super resolution (SR). In this paper, we propose a deep joint super resolution (DJSR) model to exploit both external and self similarities for SR. A Stacked Denoising Convolutional Auto Encoder (SDCAE) is first pre-trained on external examples with proper data augmentations. It is then fine-tuned with multi-scale self examples from each input, where the reliability of self examples is explicitly taken into account. We also enhance the model… Expand
Advanced Super-Resolution Using Lossless Pooling Convolutional Networks
In this paper, we present a novel deep learning-based approach for still image super-resolution, that unlike the mainstream models does not rely solely on the input low resolution image for highExpand
Super-Resolution via Image-Adapted Denoising CNNs: Incorporating External and Internal Learning
TLDR
This letter applies a recent P&P strategy to SR, and shows how it may become image-adaptive in test time, and incorporates these two independent strategies, enjoying the impressive generalization capabilities of deep learning, captured by the first and further improving it through internal learning at test time. Expand
Learning Super-Resolution Jointly From External and Internal Examples
TLDR
Joint SR is proposed to adaptively combine the advantages of both external and internal SR methods, and defines two loss functions using sparse coding-based external examples, and epitomic matching based on internal examples, as well as a corresponding adaptive weight to automatically balance their contributions according to their reconstruction errors. Expand
Deep learning based image super-resolution with coupled backpropagation
TLDR
Preliminary experiments show that SR-CBP can produce better results than state of the art single image superresolution methods based on sparse representations, and the memory and storage requirements of CAN are lesser than existing deep learning based SR methods. Expand
Blind Super-Resolution with Deep Convolutional Neural Networks
TLDR
This paper addresses blind SR using Convolutional Neural Networks and shows that such models can handle different level of blur without any a priori knowledge of the actual kernel used to produce LR images. Expand
Self-Supervised Fine-tuning for Image Enhancement of Super-Resolution Deep Neural Networks
TLDR
This paper proposes an efficient, fully self-supervised approach to remove the observed artifacts, and applies the method to image and video super-resolution neural networks and shows that the proposed framework consistently enhances the solution originally provided by the neural network. Expand
Orthogonally Regularized Deep Networks for Image Super-Resolution
TLDR
This Orthogonally Regularized Deep SR network (ORDSR) simplifies the SR task by taking advantage of image transform domain while adapting the design of transform basis to the training image set and achieves state-of-the-art SR image quality with fewer parameters than most of the deep CNN methods. Expand
Single image super-resolution using a deep encoder-decoder symmetrical network with iterative back projection
TLDR
A novel deep encoder-decoder symmetrical neural network (DEDSN) for single image SR is proposed that can achieve better performance than SRCNN and the improved DEDSN-IBP outperforms the reported state-of-the-art methods. Expand
Deep Image Super Resolution via Natural Image Priors
TLDR
This work proposes to regularize deep structures with prior knowledge about the images so that they can capture more structural information from the same limited data. Expand
Deep learning based frameworks for image super-resolution and noise-resilient super-resolution
TLDR
Experimental results show that proposed noise resilient super-resolution framework outperforms the conventional and state-of-the-art approaches in terms of PSNR and SSIM metrics. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 30 REFERENCES
Learning Super-Resolution Jointly From External and Internal Examples
TLDR
Joint SR is proposed to adaptively combine the advantages of both external and internal SR methods, and defines two loss functions using sparse coding-based external examples, and epitomic matching based on internal examples, as well as a corresponding adaptive weight to automatically balance their contributions according to their reconstruction errors. Expand
Learning a Deep Convolutional Network for Image Super-Resolution
TLDR
This work proposes a deep learning method for single image super-resolution (SR) that directly learns an end-to-end mapping between the low/high-resolution images and shows that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network. Expand
Deep Network Cascade for Image Super-resolution
TLDR
Experiments on image super-resolution demonstrate that the proposed DNC can gradually upscale a low-resolution image with the increase of network layers and achieve more promising results in visual quality as well as quantitative performance. Expand
Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion
TLDR
This work clearly establishes the value of using a denoising criterion as a tractable unsupervised objective to guide the learning of useful higher level representations. Expand
A joint perspective towards image super-resolution: Unifying external- and self-examples
TLDR
This paper constructs a unified SR formulation, and proposes an iterative joint super resolution (IJSR) algorithm to solve the optimization, which leads to an impressive improvement of SR results both quantitatively and qualitatively. Expand
Exploiting Self-similarities for Single Frame Super-Resolution
TLDR
A super-resolution method that exploits selfsimilarities and group structural information of image patches using only one single input frame and generates image pairs directly from the image pyramid of one single frame is proposed. Expand
A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution
TLDR
This work proposes A+, an improved variant of Anchored Neighborhood Regression, which combines the best qualities of ANR and SF and builds on the features and anchored regressors from ANR but instead of learning the regressors on the dictionary it uses the full training material, similar to SF. Expand
Fast Image Super-Resolution Based on In-Place Example Regression
We propose a fast regression model for practical single image super-resolution based on in-place examples, by leveraging two fundamental super-resolution approaches- learning from an externalExpand
Adaptive deconvolutional networks for mid and high level feature learning
TLDR
A hierarchical model that learns image decompositions via alternating layers of convolutional sparse coding and max pooling, relying on a novel inference scheme that ensures each layer reconstructs the input, rather than just the output of the layer directly beneath, as is common with existing hierarchical approaches. Expand
Image Denoising and Inpainting with Deep Neural Networks
TLDR
A novel approach to low-level vision problems that combines sparse coding and deep networks pre-trained with denoising auto-encoder (DA) is presented and can automatically remove complex patterns like superimposed text from an image, rather than simple patterns like pixels missing at random. Expand
...
1
2
3
...