Dual reconstruction with densely connected residual network for single image super-resolution

Chih Chung Hsu, Chia Hsiang Lin

研究成果: Conference contribution

1 引文 斯高帕斯(Scopus)

摘要

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.

原文English
主出版物標題Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
發行者Institute of Electrical and Electronics Engineers Inc.
頁面3643-3650
頁數8
ISBN(電子)9781728150239
DOIs
出版狀態Published - 2019 十月
事件17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019 - Seoul, Korea, Republic of
持續時間: 2019 十月 272019 十月 28

出版系列

名字Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019

Conference

Conference17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019
國家Korea, Republic of
城市Seoul
期間19-10-2719-10-28

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

指紋 深入研究「Dual reconstruction with densely connected residual network for single image super-resolution」主題。共同形成了獨特的指紋。

引用此