# Stable Long-Term Recurrent Video Super-Resolution

arXiv: https://arxiv.org/abs/2112.08950 · HTML: https://mlsanity.com/paper/2112.08950/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 31 references that are in the map.
- First posted on arXiv 16 Dec 2021.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [EDVR: Video Restoration with Enhanced Deformable Convolutional Networks](https://mlsanity.com/paper/1905.02716/) (2019)
- [Lipschitz regularity of deep neural networks: analysis and efficient estimation](https://mlsanity.com/paper/1805.10965/) (2018)
- [Regularisation of Neural Networks by Enforcing Lipschitz Continuity](https://mlsanity.com/paper/1804.04368/) (2018)
- [Unitary Evolution Recurrent Neural Networks](https://mlsanity.com/paper/1511.06464/) (2015)
- [Frame-Recurrent Video Super-Resolution](https://mlsanity.com/paper/1801.04590/) (2018)
- [Video Super-Resolution with Recurrent Structure-Detail Network](https://mlsanity.com/paper/2008.00455/) (2020)
- [The Singular Values of Convolutional Layers](https://mlsanity.com/paper/1805.10408/) (2018)
- [Full-Capacity Unitary Recurrent Neural Networks](https://mlsanity.com/paper/1611.00035/) (2016)
- [On orthogonality and learning recurrent networks with long term dependencies](https://mlsanity.com/paper/1702.00071/) (2017)
- [Video Super-resolution with Temporal Group Attention](https://mlsanity.com/paper/2007.10595/) (2020)
- [Efficient Video Super-Resolution through Recurrent Latent Space Propagation](https://mlsanity.com/paper/1909.08080/) (2019)
- [Stable Recurrent Models](https://mlsanity.com/paper/1805.10369/) (2018)
- [Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections](https://mlsanity.com/paper/1612.00188/) (2016)
- [Stable Rank Normalization for Improved Generalization in Neural Networks and GANs](https://mlsanity.com/paper/1906.04659/) (2019)
- [Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization](https://mlsanity.com/paper/1803.09327/) (2018)
- [End-To-End Trainable Video Super-Resolution Based on a New Mechanism for Implicit Motion Estimation and Compensation](https://mlsanity.com/paper/2001.01162/) (2020)
- [Kronecker Recurrent Units](https://mlsanity.com/paper/1705.10142/) (2017)
- [Diagnosing and Preventing Instabilities in Recurrent Video Processing](https://mlsanity.com/paper/2010.05099/) (2020)

## Built on by (most cited first, 6 of 6)

- [FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring](https://mlsanity.com/paper/2401.03707/) (2024)
- [Local-Global Temporal Difference Learning for Satellite Video Super-Resolution](https://mlsanity.com/paper/2304.04421/) (2023)
- [Low-Resource Video Super-Resolution using Memory, Wavelets, and Deformable Convolutions](https://mlsanity.com/paper/2502.01816/) (2025)
- [Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects](https://mlsanity.com/paper/2509.22692/) (2025)
- [Time-series Initialization and Conditioning for Video-agnostic Stabilization of Video Super-Resolution using Recurrent Networks](https://mlsanity.com/paper/2403.15832/) (2024)
- [FMA-Net++: Motion- and Exposure-Aware Joint Video Super-Resolution and Deblurring](https://mlsanity.com/paper/2512.04390/) (2025)

## Abstract (arXiv)

Recurrent models have gained popularity in deep learning (DL) based video super-resolution (VSR), due to their increased computational efficiency, temporal receptive field and temporal consistency compared to sliding-window based models. However, when inferring on long video sequences presenting low motion (i.e. in which some parts of the scene barely move), recurrent models diverge through recurrent processing, generating high frequency artifacts. To the best of our knowledge, no study about VSR pointed out this instability problem, which can be critical for some real-world applications. Video surveillance is a typical example where such artifacts would occur, as both the camera and the scene stay static for a long time. In this work, we expose instabilities of existing recurrent VSR networks on long sequences with low motion. We demonstrate it on a new long sequence dataset Quasi-Static Video Set, that we have created. Finally, we introduce a new framework of recurrent VSR networks that is both stable and competitive, based on Lipschitz stability theory. We propose a new recurrent VSR network, coined Middle Recurrent Video Super-Resolution (MRVSR), based on this framework. We empirically show its competitive performance on long sequences with low motion.