Deep Super-Resolution Network for Single Image Super-Resolution with Realistic Degradations

@article{Umer2019DeepSN,
  title={Deep Super-Resolution Network for Single Image Super-Resolution with Realistic Degradations},
  author={Rao Muhammad Umer and Gian Luca Foresti and Christian Micheloni},
  journal={Proceedings of the 13th International Conference on Distributed Smart Cameras},
  year={2019}
}
Single Image Super-Resolution (SISR) aims to generate a high-resolution (HR) image of a given low-resolution (LR) image. [...] Key Method To address this issue, we propose a deep SISR network that works for blur kernels of different sizes, and different noise levels in an unified residual CNN-based denoiser network, which significantly improves a practical CNN-based super-resolver for real applications. Extensive experimental results on synthetic LR datasets and real images demonstrate that our proposed method…Expand
A Deep Residual Star Generative Adversarial Network for multi-domain Image Super-Resolution
TLDR
A deep Super-Resolution Residual StarGAN (SR2*GAN), a novel and scalable approach that super-resolves the LR images for the multiple LR domains using only a single model. Expand
Deep Iterative Residual Convolutional Network for Single Image Super-Resolution
TLDR
This work proposes a deep Iterative Super-Resolution Residual Convolutional Network (ISRResCNet) that exploits the powerful image regularization and large-scale optimization techniques by training the deep network in an iterative manner with a residual learning approach. Expand
Deep Generative Adversarial Residual Convolutional Networks for Real-World Super-Resolution
TLDR
A deep Super-Resolution Residual Convolutional Generative Adversarial Network (SRResCGAN1) to follow the real-world degradation settings by adversarial training the model with pixel-wise supervision in the HR domain from its generated LR counterpart. Expand
Deep Cyclic Generative Adversarial Residual Convolutional Networks for Real Image Super-Resolution
TLDR
This work proposes the Super-Resolution Residual Cyclic Generative Adversarial Network (SRResCycGAN) by training with a generative adversarial network (GAN) framework for the LR to HR domain translation in an end-to-end manner and demonstrates that the proposed approach achieves comparable results as the other state-of-art methods. Expand
RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural Network
TLDR
A Raw Burst Super-Resolution Iterative Convolutional Neural Network (RBSRICNN1) that follows the burst photography pipeline as a whole by a forward (physical) model that solves the problem with classical image regularization, convex optimization, and deep learning techniques, compared to existing black-box datadriven methods. Expand

References

SHOWING 1-10 OF 48 REFERENCES
Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
TLDR
Extensive experimental results show that the proposed convolutional super-resolution network not only can produce favorable results on multiple degradations but also is computationally efficient, providing a highly effective and scalable solution to practical SISR applications. Expand
Image Super-Resolution Using Deep Convolutional Networks
We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deepExpand
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
TLDR
This paper presents the first convolutional neural network capable of real-time SR of 1080p videos on a single K2 GPU and introduces an efficient sub-pixel convolution layer which learns an array of upscaling filters to upscale the final LR feature maps into the HR output. Expand
Enhanced Deep Residual Networks for Single Image Super-Resolution
TLDR
This paper develops an enhanced deep super-resolution network (EDSR) with performance exceeding those of current state-of-the-art SR methods, and proposes a new multi-scale deepsuper-resolution system (MDSR) and training method, which can reconstruct high-resolution images of different upscaling factors in a single model. 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
Universal Denoising Networks : A Novel CNN Architecture for Image Denoising
TLDR
A novel network architecture for learning discriminative image models that are employed to efficiently tackle the problem of grayscale and color image denoising is designed and two different variants are introduced, which achieve excellent results under additive white Gaussian noise. Expand
Accurate Image Super-Resolution Using Very Deep Convolutional Networks
TLDR
This work presents a highly accurate single-image superresolution (SR) method using a very deep convolutional network inspired by VGG-net used for ImageNet classification and uses extremely high learning rates enabled by adjustable gradient clipping. Expand
Non-local Color Image Denoising with Convolutional Neural Networks
  • Stamatios Lefkimmiatis
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
TLDR
This work proposes a novel deep network architecture for grayscale and color image denoising that is based on a non-local image model and highlights a direct link of the proposed non- local models to convolutional neural networks. Expand
Accurate Blur Models vs. Image Priors in Single Image Super-resolution
TLDR
It is found that an accurate blur model is more important than a sophisticated image prior in reconstructing raw lowers images acquired by an actual camera and the default blur models of various SR algorithms may differ from the camera blur, typically leading to over-smoothed results. Expand
Learning Deep CNN Denoiser Prior for Image Restoration
TLDR
Experimental results demonstrate that the learned set of denoisers can not only achieve promising Gaussian denoising results but also can be used as prior to deliver good performance for various low-level vision applications. Expand
...
1
2
3
4
5
...