Image Super-resolution with An Enhanced Group Convolutional Neural Network

@article{Tian2022ImageSW,
  title={Image Super-resolution with An Enhanced Group Convolutional Neural Network},
  author={Chunwei Tian and Yixuan Yuan and Shichao Zhang and Chia-Wen Lin and Wangmeng Zuo and David Zhang},
  journal={Neural networks : the official journal of the International Neural Network Society},
  year={2022},
  volume={153},
  pages={
          373-385
        }
}
CNNs with strong learning abilities are widely chosen to resolve super-resolution problem. However, CNNs depend on deeper network architectures to improve performance of image super-resolution, which may increase computational cost in general. In this paper, we present an enhanced super-resolution group CNN (ESRGCNN) with a shallow architecture by fully fusing deep and wide channel features to extract more accurate low-frequency information in terms of correlations of different channels in… 
[PDF] Semantic Reader
15 Citations
Background Citations
1
Methods Citations
2

15 Citations

Restoration and enhancement on low exposure raw images by joint demosaicing and denoising

An Efficient Hybrid Classifier for MRI Brain Images Classification Using Machine Learning Based Naive Bayes Algorithm

The main purpose of the proposed mathematical model is to increase the accuracy rate of normal image classification and abnormal image classification with respect to classification methods like RS with RF, RS with BN and FF-ANN.

Image Super-Resolution using Efficient Striped Window Transformer

The normalization layer in the transformer is revisited and a concise and efficient transformer structure is designed to build the efficient striped window transformer (ESWT), which requires fewer parameters, incurs faster inference, smaller FLOPs, and less memory consumption, making it a promising solution for LSR.

A Study on Pine Larva Detection System Using Swin Transformer and Cascade R-CNN Hybrid Model

Pine trees are more vulnerable to diseases and pests than other trees, so prevention and management are necessary in advance. In this paper, two models of deep learning were mixed to quickly check…

Self-attention learning network for face super-resolution

GCS-YOLOV4-Tiny: A lightweight group convolution network for multi-stage fruit detection.

Fruits require different planting techniques at different growth stages. Traditionally, the maturity stage of fruit is judged visually, which is time-consuming and labor-intensive. Fruits differ in…

GEO: A Computational Design Framework for Automotive Exterior Facelift

Exterior facelift has become an effective method for automakers to boost the consumers’ interest in an existing car model before it is redesigned. To support the automotive facelift design process,…

An Improved U-Net for Watermark Removal

An improved watermark removal U-net (IWRU-net), which uses randomly distributed blind watermarks to implement a blind watermark Removal model and shows that the proposed method is superior to other popular watermarks removal methods in terms of quantitative and qualitative evaluations.

Classification of Cacao Pod if Healthy or Attack by Pest or Black Pod Disease Using Deep Learning Algorithm

Using the trained lightweight model, it is possible to accurately and automate the classification of cacao pod conditions and to integrate it with hardware monitoring/surveillance devices to perform real-time classification of the cacaoPod condition on the actual field.

Iterative Dual CNNs for Image Deblurring

The proposed method has an excellent effect of deblurring on a real blurred image dataset and is suitable for various real application scenes and a multiscale iterative strategy that effectively improves the robustness and precision of the model.

References

SHOWING 1-10 OF 77 REFERENCES

Image Quality Metrics: PSNR vs. SSIM

  • Alain HoréD. Ziou
  • Computer Science
    2010 20th International Conference on Pattern Recognition
  • 2010
A simple mathematical relationship is derived between the peak-signal-to-noise ratio and the structural similarity index measure which works for various kinds of image degradations such as Gaussian blur, additive Gaussian white noise, jpeg and jpeg2000 compression.

Channel-Wise and Spatial Feature Modulation Network for Single Image Super-Resolution

A channel-wise and spatial feature modulation (CSFM) network in which a series of feature modulation memory (FMM) modules are cascaded with a densely connected structure to transform shallow features to high informative features and maintain long-term information for image super-resolution.

Residual Dense Network for Image Super-Resolution

This paper proposes residual dense block (RDB) to extract abundant local features via dense connected convolutional layers and uses global feature fusion in RDB to jointly and adaptively learn global hierarchical features in a holistic way.

Iterative correction of intersymbol interference: Turbo-equalization

The results obtained show that turbo-equalization manages to overcome multipath effects, totally on Gauss channels, and partially but still satisfactorily on Rayleigh channels.

Structure-Preserving Image Super-Resolution via Contextualized Multitask Learning

This paper develops a contextualized multitask learning framework that first extracts convolutional features from the input LR image and applies one deconvolutional module to interpolate the LR feature maps in a content-adaptive way and demonstrates the effectiveness of the method on achieving both higher restoration quality and computational efficiency compared with several state-of-the-art SR approaches.

Single image super-resolution from transformed self-exemplars

This paper expands the internal patch search space by allowing geometric variations, and proposes a compositional model to simultaneously handle both types of transformations to accommodate local shape variations.

Feedback Network for Image Super-Resolution

An image super-resolution feedback network (SRFBN) is proposed to refine low-level representations with high-level information by using hidden states in a recurrent neural network (RNN) with constraints to achieve such feedback manner.

Fast, Accurate, and, Lightweight Super-Resolution with Cascading Residual Network

This paper designs an architecture that implements a cascading mechanism upon a residual network that achieves performance comparable to that of state-of-the-art methods and presents variant models of the proposed cascading residual network to further improve efficiency.

Image Super-Resolution via Deep Recursive Residual Network

This paper proposes a very deep CNN model (up to 52 convolutional layers) named Deep Recursive Residual Network (DRRN) that strives for deep yet concise networks, and recursive learning is used to control the model parameters while increasing the depth.

Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections

This paper proposes to symmetrically link convolutional and de-convolutional layers with skip-layer connections, with which the training converges much faster and attains a higher-quality local optimum, making training deep networks easier and achieving restoration performance gains consequently.
...