# An Efficient Network Design for Face Video Super-resolution

arXiv: https://arxiv.org/abs/2109.13626 · HTML: https://mlsanity.com/paper/2109.13626/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 28 Sep 2021.

## Builds on (most cited first, 8 of 8)

- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016)
- [Deep Face Recognition: A Survey](https://mlsanity.com/paper/1804.06655/) (2018)
- [Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation](https://mlsanity.com/paper/1611.05250/) (2016)
- [Detail-revealing Deep Video Super-resolution](https://mlsanity.com/paper/1704.02738/) (2017)
- [Deep Video Super-Resolution using HR Optical Flow Estimation](https://mlsanity.com/paper/2001.02129/) (2020)
- [Learning for Video Super-Resolution through HR Optical Flow Estimation](https://mlsanity.com/paper/1809.08573/) (2018)

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

- [Towards Lightweight Super-Resolution with Dual Regression Learning](https://mlsanity.com/paper/2207.07929/) (2022)
- [A Survey of Deep Learning Video Super-Resolution](https://mlsanity.com/paper/2506.03216/) (2025)
- [A Lightweight Recurrent Grouping Attention Network for Video Super-Resolution](https://mlsanity.com/paper/2309.13940/) (2023)
- [Collaborative Feature Aggregation for Face Super-Resolution and Robust Re-Identification](https://mlsanity.com/paper/2607.28130/) (2026)

## Abstract (arXiv)

Face video super-resolution algorithm aims to reconstruct realistic face details through continuous input video sequences. However, existing video processing algorithms usually contain redundant parameters to guarantee different super-resolution scenes. In this work, we focus on super-resolution of face areas in original video scenes, while rest areas are interpolated. This specific super-resolved task makes it possible to cut redundant parameters in general video super-resolution networks. We construct a dataset consisting entirely of face video sequences for network training and evaluation, and conduct hyper-parameter optimization in our experiments. We use three combined strategies to optimize the network parameters with a simultaneous train-evaluation method to accelerate optimization process. Results show that simultaneous train-evaluation method improves the training speed and facilitates the generation of efficient networks. The generated network can reduce at least 52.4% parameters and 20.7% FLOPs, achieve better performance on PSNR, SSIM compared with state-of-art video super-resolution algorithms. When processing 36x36x1x3 input video frame sequences, the efficient network provides 47.62 FPS real-time processing performance. We name our proposal as hyper-parameter optimization for face Video Super-Resolution (HO-FVSR), which is open-sourced at https://github.com/yphone/efficient-network-for-face-VSR.