# Learning for Video Super-Resolution through HR Optical Flow Estimation

arXiv: https://arxiv.org/abs/1809.08573 · HTML: https://mlsanity.com/paper/1809.08573/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Sep 2018.

## Built on by (most cited first, 24 of 24)

- [RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolution](https://mlsanity.com/paper/2203.14186/) (2022)
- [NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer](https://mlsanity.com/paper/2303.06919/) (2023)
- [Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning](https://mlsanity.com/paper/2205.05264/) (2022)
- [Deep Parametric 3D Filters for Joint Video Denoising and Illumination Enhancement in Video Super Resolution](https://mlsanity.com/paper/2207.01797/) (2022)
- [Towards Interpretable Video Super-Resolution via Alternating Optimization](https://mlsanity.com/paper/2207.10765/) (2022)
- [Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsampling](https://mlsanity.com/paper/2103.11744/) (2021)
- [Real-Time Super-Resolution System of 4K-Video Based on Deep Learning](https://mlsanity.com/paper/2107.05307/) (2021)
- [From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer Paradigm](https://mlsanity.com/paper/2306.06388/) (2023)
- [STDAN: Deformable Attention Network for Space-Time Video Super-Resolution](https://mlsanity.com/paper/2203.06841/) (2022)
- [NegVSR: Augmenting Negatives for Generalized Noise Modeling in Real-World Video Super-Resolution](https://mlsanity.com/paper/2305.14669/) (2023)
- [Zooming SlowMo: An Efficient One-Stage Framework for Space-Time Video Super-Resolution](https://mlsanity.com/paper/2104.07473/) (2021)
- [Gradient Forward-Propagation for Large-Scale Temporal Video Modelling](https://mlsanity.com/paper/2106.08318/) (2021)
- [Towards True Detail Restoration for Super-Resolution: A Benchmark and a Quality Metric](https://mlsanity.com/paper/2203.08923/) (2022)
- [An Efficient Network Design for Face Video Super-resolution](https://mlsanity.com/paper/2109.13626/) (2021)
- [You Only Align Once: Bidirectional Interaction for Spatial-Temporal Video Super-Resolution](https://mlsanity.com/paper/2207.06345/) (2022)
- [Learning Spatio-Temporal Downsampling for Effective Video Upscaling](https://mlsanity.com/paper/2203.08140/) (2022)
- [SR+Codec: a Benchmark of Super-Resolution for Video Compression Bitrate Reduction](https://mlsanity.com/paper/2305.04844/) (2023)
- [TransNet: A Transfer Learning-Based Network for Human Action Recognition](https://mlsanity.com/paper/2309.06951/) (2023)
- [Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects](https://mlsanity.com/paper/2509.22692/) (2025)
- [Towards Robust and Generalizable Continuous Space-Time Video Super-Resolution with Events](https://mlsanity.com/paper/2510.03833/) (2025)
- [Video Super-Resolution with Long-Term Self-Exemplars](https://mlsanity.com/paper/2106.12778/) (2021)
- [Information Prebuilt Recurrent Reconstruction Network for Video Super-Resolution](https://mlsanity.com/paper/2112.05755/) (2021)
- [Lightweight Image Enhancement Network for Mobile Devices Using Self-Feature Extraction and Dense Modulation](https://mlsanity.com/paper/2205.00853/) (2022)
- [Real-Time Neural Video Recovery and Enhancement on Mobile Devices](https://mlsanity.com/paper/2307.12152/) (2023)

## Abstract (arXiv)

Video super-resolution (SR) aims to generate a sequence of high-resolution (HR) frames with plausible and temporally consistent details from their low-resolution (LR) counterparts. The generation of accurate correspondence plays a significant role in video SR. It is demonstrated by traditional video SR methods that simultaneous SR of both images and optical flows can provide accurate correspondences and better SR results. However, LR optical flows are used in existing deep learning based methods for correspondence generation. In this paper, we propose an end-to-end trainable video SR framework to super-resolve both images and optical flows. Specifically, we first propose an optical flow reconstruction network (OFRnet) to infer HR optical flows in a coarse-to-fine manner. Then, motion compensation is performed according to the HR optical flows. Finally, compensated LR inputs are fed to a super-resolution network (SRnet) to generate the SR results. Extensive experiments demonstrate that HR optical flows provide more accurate correspondences than their LR counterparts and improve both accuracy and consistency performance. Comparative results on the Vid4 and DAVIS-10 datasets show that our framework achieves the state-of-the-art performance.