# RBPGAN: Recurrent Back-Projection GAN for Video Super Resolution

arXiv: https://arxiv.org/abs/2311.09178 · HTML: https://mlsanity.com/paper/2311.09178/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 15 Nov 2023.

## Builds on (most cited first, 9 of 9)

- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [EDVR: Video Restoration with Enhanced Deformable Convolutional Networks](https://mlsanity.com/paper/1905.02716/) (2019)
- [Assessing Generative Models via Precision and Recall](https://mlsanity.com/paper/1806.00035/) (2018)
- [Recurrent Back-Projection Network for Video Super-Resolution](https://mlsanity.com/paper/1903.10128/) (2019)
- [Unpaired Motion Style Transfer from Video to Animation](https://mlsanity.com/paper/2005.05751/) (2020)
- [Avoiding Latent Variable Collapse With Generative Skip Models](https://mlsanity.com/paper/1807.04863/) (2018)
- [Generative Adversarial Networks and Perceptual Losses for Video Super-Resolution](https://mlsanity.com/paper/1806.05764/) (2018)
- [Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation](https://mlsanity.com/paper/1811.09393/) (2018)

## Abstract (arXiv)

Recently, video super resolution (VSR) has become a very impactful task in the area of Computer Vision due to its various applications. In this paper, we propose Recurrent Back-Projection Generative Adversarial Network (RBPGAN) for VSR in an attempt to generate temporally coherent solutions while preserving spatial details. RBPGAN integrates two state-of-the-art models to get the best in both worlds without compromising the accuracy of produced video. The generator of the model is inspired by RBPN system, while the discriminator is inspired by TecoGAN. We also utilize Ping-Pong loss to increase temporal consistency over time. Our contribution together results in a model that outperforms earlier work in terms of temporally consistent details, as we will demonstrate qualitatively and quantitatively using different datasets.