GUN: Gradual Upsampling Network for Single Image Super-Resolution

  title={GUN: Gradual Upsampling Network for Single Image Super-Resolution},
  author={Yang Zhao and Guoqing Li and Wenjun Xie and Wei Jia and Hai Min and Xiaoping Liu},
  journal={IEEE Access},
In this paper, an efficient super-resolution (SR) method based on deep convolutional neural network (CNN) is proposed, namely gradual upsampling network (GUN). Recent CNN-based SR methods often preliminarily magnify the low-resolution (LR) input to high-resolution (HR) input and then reconstruct the HR input, or directly reconstruct the LR input and then recover the HR result at the last layer. The proposed GUN utilizes a gradual process instead of these two commonly used frameworks. The GUN… 

Figures and Tables from this paper

Single Image Super-Resolution using Adaptive Upsampling Convolutional Network

  • Peng LiuYing HongYan Liu
  • Computer Science
    2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC)
  • 2019
An adaptive upsampling convolutional network for single image superresolution that can recovery the fine texture details for a large upscaling factor and outperforms many other state-of-theart super-resolution methods.

Multi-scale Xception based depthwise separable convolution for single image super-resolution

A new architecture inspired by ResNet and Xception networks is proposed, which enable a significant drop in the number of network parameters and improve the processing speed to obtain the SR results.

A Novel Multi-Scale Adaptive Convolutional Network for Single Image Super-Resolution

A novel multi-scale adaptive convolutional network that can enhance the combination of various levels features and provide different ranges of image context for super-resolution (SR) reconstruction and achieves the best super- resolution reconstruction among the state-of-the-art SR methods.

Deep Differential Convolutional Network for Single Image Super-Resolution

The experimental results prove that the proposed DCN is superior to many state-of-the-art super-resolution methods in terms of both peak signal-to-noise ratio (PSNR) and structural similarity index metrics (SSIM).

IRGUN : Improved Residue Based Gradual Up-Scaling Network for Single Image Super Resolution

A novel Improved Residual based Gradual Up-Scaling Network (IRGUN) to improve the quality of the super-resolved image for a large magnification factor and recovers fine details effectively at large (8X) magnification factors.

Multimedia super-resolution via deep learning: A survey

  • K. Hayat
  • Computer Science
    Digit. Signal Process.
  • 2018

Super-Resolution via Deep Learning

State-of-the-Art Development of Complex Systems and Their Simulation Methods

The research on complex systems is different from that on general systems because the former must consider self-organization, emergence, uncertainty, predetermination, and evolution. As an important…

A Deep Convolutional Neural Network With Multiscale Feature Dynamic Fusion for InSAR Phase Filtering

  • Wang YangYi He Yali Zhang
  • Engineering
    IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • 2022
Interferometric phase filtering is a crucial step in the interferometric synthetic aperture radar (InSAR) data processing, which is also important for improving the accuracy of topography mapping and…



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 deep…

An information fidelity criterion for image quality assessment using natural scene statistics

This paper proposes a novel information fidelity criterion that is based on natural scene statistics and derives a novel QA algorithm that provides clear advantages over the traditional approaches and outperforms current methods in testing.

Beta Process Joint Dictionary Learning for Coupled Feature Spaces with Application to Single Image Super-Resolution

  • Li HeH. QiR. Zaretzki
  • Computer Science
    2013 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
This paper addresses the problem of learning over-complete dictionaries for the coupled feature spaces, where the learned dictionaries also reflect the relationship between the two spaces. A Bayesian…

Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution

This work proposes a bidirectional recurrent convolutional network for efficient multi-frame SR, different from vanilla RNNs, which has a low computational complexity and runs orders of magnitude faster than other multi- frame methods.

Image Super-Resolution by TV-Regularization and Bregman Iteration

A new time dependent convolutional model for super-resolution based on a constrained variational model that uses the total variation of the signal as a regularizing functional and an iterative refinement procedure based on Bregman iteration to improve spatial resolution is proposed.

Depth Map Super-Resolution by Deep Multi-Scale Guidance

A new method to address the problem of depth map super resolution in which a high-resolution (HR) depth map is inferred from a LR depth map and an additional HR intensity image of the same scene is presented.

NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results

This paper reviews the first challenge on single image super-resolution (restoration of rich details in an low resolution image) with focus on proposed solutions and results and gauges the state-of-the-art in single imagesuper-resolution.

Enhanced Deep Residual Networks for Single Image Super-Resolution

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.

Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution

This paper proposes the Laplacian Pyramid Super-Resolution Network (LapSRN) to progressively reconstruct the sub-band residuals of high-resolution images and generates multi-scale predictions in one feed-forward pass through the progressive reconstruction, thereby facilitates resource-aware applications.