Papers › Cascade Convolutional Neural Network for Image Super-Resolution

Cascade Convolutional Neural Network for Image Super-Resolution

24 Aug 2020arXiv:2008.10329archive 2025-07-28

Jianwei Zhang, zhenxing Wang, yuhui Zheng, Guoqing Zhang

With the development of the super-resolution convolutional neural network (SRCNN), deep learning technique has been widely applied in the field of image super-resolution. Previous works mainly focus on optimizing the structure of SRCNN, which have been achieved well performance in speed and restoration quality for image super-resolution. However, most of these approaches only consider a specific scale image during the training process, while ignoring the relationship between different scales of images. Motivated by this concern, in this paper, we propose a cascaded convolution neural network for image super-resolution (CSRCNN), which includes three cascaded Fast SRCNNs and each Fast SRCNN can process a specific scale image. Images of different scales can be trained simultaneously and the learned network can make full use of the information resided in different scales of images. Extensive experiments show that our network can achieve well performance for image SR.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Super-ResolutionSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Super-Resolution BSD200 - 2x upscaling CSRCNN PSNR 32.92 #1 of 1 Archive leaderboard report
Image Super-Resolution BSD200 - 2x upscaling CSRCNN SSIM 0.9122 #1 of 1 Archive leaderboard report
Image Super-Resolution Set14 - 2x upscaling CSRCNN PSNR 34.34 #13 of 35 Archive leaderboard report
Image Super-Resolution Set14 - 2x upscaling CSRCNN SSIM 0.9240 #13 of 35 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling CSRCNN PSNR 28.47 #63 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling CSRCNN SSIM 0.7720 #63 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 8x upscaling CSRCNN PSNR 24.30 #6 of 7 Archive leaderboard report
Image Super-Resolution Set14 - 8x upscaling CSRCNN SSIM 0.614 #6 of 7 Archive leaderboard report
Image Super-Resolution Set5 - 2x upscaling CSRCNN PSNR 37.45 #37 of 41 Archive leaderboard report
Image Super-Resolution Set5 - 2x upscaling CSRCNN SSIM 0.9570 #37 of 41 Archive leaderboard report
Image Super-Resolution Set5 - 8x upscaling CSRCNN PSNR 25.74 #8 of 8 Archive leaderboard report
Image Super-Resolution Set5 - 8x upscaling CSRCNN SSIM 0.715 #8 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections