Robust Single-Image Super-Resolution via CNNs and TV-TV Minimization

Single-image super-resolution is the process of increasing the resolution of an image, obtaining a high-resolution (HR) image from a low-resolution (LR) one. By leveraging large training datasets, convolutional neural networks (CNNs) currently achieve the state-of-the-art performance in this task. Y...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing 2021, Vol.30, p.7830-7841
Main Authors: Vella, Marija, Mota, Joao F. C.
Format: Article
Language:English
Subjects:
Artificial neural networks
Consistency
convolutional neural networks. (CNNs)
Datasets
Image quality
Image reconstruction
Image resolution
Image super-resolution
Minimization
Optimization
Post-production processing
prior information
Robustness
Task analysis
Testing
Training
ℓ₁-ℓ₁ minimization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Single-image super-resolution is the process of increasing the resolution of an image, obtaining a high-resolution (HR) image from a low-resolution (LR) one. By leveraging large training datasets, convolutional neural networks (CNNs) currently achieve the state-of-the-art performance in this task. Yet, during testing/deployment, they fail to enforce consistency between the HR and LR images: if we downsample the output HR image, it never matches its LR input. Based on this observation, we propose to post-process the CNN outputs with an optimization problem that we call TV-TV minimization , which enforces consistency. As our extensive experiments show, such post-processing not only improves the quality of the images, in terms of PSNR and SSIM, but also makes the super-resolution task robust to operator mismatch, i.e., when the true downsampling operator is different from the one used to create the training dataset.
ISSN:1057-7149
1941-0042
DOI:10.1109/TIP.2021.3108907