Dual Reconstruction with Densely Connected Residual Network for Single Image Super-Resolution

11/20/2019
by   Chih-Chung Hsu, et al.
0

Deep learning-based single image super-resolution enables very fast and high-visual-quality reconstruction. Recently, an enhanced super-resolution based on generative adversarial network (ESRGAN) has achieved excellent performance in terms of both qualitative and quantitative quality of the reconstructed high-resolution image. In this paper, we propose to add one more shortcut between two dense-blocks, as well as add shortcut between two convolution layers inside a dense-block. With this simple strategy of adding more shortcuts in the proposed network, it enables a faster learning process as the gradient information can be back-propagated more easily. Based on the improved ESRGAN, the dual reconstruction is proposed to learn different aspects of the super-resolved image for judiciously enhancing the quality of the reconstructed image. In practice, the super-resolution model is pre-trained solely based on pixel distance, followed by fine-tuning the parameters in the model based on adversarial loss and perceptual loss. Finally, we fuse two different models by weighted-summing their parameters to obtain the final super-resolution model. Experimental results demonstrated that the proposed method achieves excellent performance in the real-world image super-resolution challenge. We have also verified that the proposed dual reconstruction does further improve the quality of the reconstructed image in terms of both PSNR and SSIM.

READ FULL TEXT

page 1

page 3

page 6

research
01/17/2022

Dual Perceptual Loss for Single Image Super-Resolution Using ESRGAN

The proposal of perceptual loss solves the problem that per-pixel differ...
research
12/17/2019

Adaptive Densely Connected Super-Resolution Reconstruction

For a better performance in single image super-resolution(SISR), we pres...
research
10/20/2022

Single Image Super-Resolution Using Lightweight Networks Based on Swin Transformer

Image super-resolution reconstruction is an important task in the field ...
research
11/17/2021

Image Super-Resolution Using T-Tetromino Pixels

For modern high-resolution imaging sensors, pixel binning is performed i...
research
04/09/2018

A Fully Progressive Approach to Single-Image Super-Resolution

Recent deep learning approaches to single image super-resolution have ac...
research
06/17/2019

Hierarchical Back Projection Network for Image Super-Resolution

Deep learning based single image super-resolution methods use a large nu...
research
04/08/2020

Time accelerated image super-resolution using shallow residual feature representative network

The recent advances in deep learning indicate significant progress in th...

Please sign up or login with your details

Forgot password? Click here to reset