DeepAI AI Chat
Log In Sign Up

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

by   Chih-Chung Hsu, et al.

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.


page 1

page 3

page 6


Dual Perceptual Loss for Single Image Super-Resolution Using ESRGAN

The proposal of perceptual loss solves the problem that per-pixel differ...

Adaptive Densely Connected Super-Resolution Reconstruction

For a better performance in single image super-resolution(SISR), we pres...

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

Image super-resolution reconstruction is an important task in the field ...

Image Super-Resolution Using T-Tetromino Pixels

For modern high-resolution imaging sensors, pixel binning is performed i...

A Fully Progressive Approach to Single-Image Super-Resolution

Recent deep learning approaches to single image super-resolution have ac...

Hierarchical Back Projection Network for Image Super-Resolution

Deep learning based single image super-resolution methods use a large nu...

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

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