# A Single Video Super-Resolution GAN for Multiple Downsampling Operators based on Pseudo-Inverse Image Formation Models

arXiv: https://arxiv.org/abs/1907.01399 · HTML: https://mlsanity.com/paper/1907.01399/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2019.

## Built on by (most cited first, 3 of 3)

- [Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects](https://mlsanity.com/paper/2509.22692/) (2025)
- [A General Method to Incorporate Spatial Information into Loss Functions for GAN-based Super-resolution Models](https://mlsanity.com/paper/2403.10589/) (2024)
- [VDPI: Video Deblurring with Pseudo-inverse Modeling](https://mlsanity.com/paper/2409.00777/) (2024)

## Abstract (arXiv)

The popularity of high and ultra-high definition displays has led to the need for methods to improve the quality of videos already obtained at much lower resolutions. Current Video Super-Resolution methods are not robust to mismatch between training and testing degradation models since they are trained against a single degradation model (usually bicubic downsampling). This causes their performance to deteriorate in real-life applications. At the same time, the use of only the Mean Squared Error during learning causes the resulting images to be too smooth. In this work we propose a new Convolutional Neural Network for video super resolution which is robust to multiple degradation models. During training, which is performed on a large dataset of scenes with slow and fast motions, it uses the pseudo-inverse image formation model as part of the network architecture in conjunction with perceptual losses, in addition to a smoothness constraint that eliminates the artifacts originating from these perceptual losses. The experimental validation shows that our approach outperforms current state-of-the-art methods and is robust to multiple degradations.