Correction filter for single image super-resolution: Robustifying off-the-shelf deep super-resolvers

Shady Abu Hussein, Tom Tirer, Raja Giryes

Research output: Contribution to journalConference articlepeer-review

51 Scopus citations


The single image super-resolution task is one of the most examined inverse problems in the past decade. In the recent years, Deep Neural Networks (DNNs) have shown superior performance over alternative methods when the acquisition process uses a fixed known downscaling kernel—typically a bicubic kernel. However, several recent works have shown that in practical scenarios, where the test data mismatch the training data (e.g. when the downscaling kernel is not the bicubic kernel or is not available at training), the leading DNN methods suffer from a huge performance drop. Inspired by the literature on generalized sampling, in this work we propose a method for improving the performance of DNNs that have been trained with a fixed kernel on observations acquired by other kernels. For a known kernel, we design a closed-form correction filter that modifies the low-resolution image to match one which is obtained by another kernel (e.g. bicubic), and thus improves the results of existing pre-trained DNNs. For an unknown kernel, we extend this idea and propose an algorithm for blind estimation of the required correction filter. We show that our approach outperforms other super-resolution methods, which are designed for general downscaling kernels.

Original languageEnglish
Article number9156619
Pages (from-to)1425-1434
Number of pages10
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
StatePublished - 2020
Event2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 - Virtual, Online, United States
Duration: 14 Jun 202019 Jun 2020


FundersFunder number
Horizon 2020 Framework Programme757497


    Dive into the research topics of 'Correction filter for single image super-resolution: Robustifying off-the-shelf deep super-resolvers'. Together they form a unique fingerprint.

    Cite this