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

arXiv: https://arxiv.org/abs/2004.00843 · HTML: https://mlsanity.com/paper/2004.00843/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Apr 2020.

## Built on by (most cited first, 4 of 4)

- [Enhanced Hyperspectral Image Super-Resolution via RGB Fusion and TV-TV Minimization](https://mlsanity.com/paper/2106.07066/) (2021)
- [Measurement-Consistent Networks via a Deep Implicit Layer for Solving Inverse Problems](https://mlsanity.com/paper/2211.03177/) (2022)
- [SRTransGAN: Image Super-Resolution using Transformer based Generative Adversarial Network](https://mlsanity.com/paper/2312.01999/) (2023)
- [The Best of Both Worlds: a Framework for Combining Degradation Prediction with High Performance Super-Resolution Networks](https://mlsanity.com/paper/2211.05018/) (2022)

## Abstract (arXiv)

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.