# GRNN:Recurrent Neural Network based on Ghost Features for Video Super-Resolution

arXiv: https://arxiv.org/abs/2505.10577 · HTML: https://mlsanity.com/paper/2505.10577/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 31 references that are in the map.
- First posted on arXiv 14 May 2025.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [Recurrent Neural Network Regularization](https://mlsanity.com/paper/1409.2329/) (2014)
- [Frame-Recurrent Video Super-Resolution](https://mlsanity.com/paper/1801.04590/) (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)
- [Recurrent Back-Projection Network for Video Super-Resolution](https://mlsanity.com/paper/1903.10128/) (2019)
- [MuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution](https://mlsanity.com/paper/2007.11803/) (2020)
- [Understanding Deformable Alignment in Video Super-Resolution](https://mlsanity.com/paper/2009.07265/) (2020)
- [Video Super Resolution Based on Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2007.12928/) (2020)
- [Revisiting Temporal Modeling for Video Super-resolution](https://mlsanity.com/paper/2008.05765/) (2020)
- [Deformable 3D Convolution for Video Super-Resolution](https://mlsanity.com/paper/2004.02803/) (2020)
- [Deformable Non-local Network for Video Super-Resolution](https://mlsanity.com/paper/1909.10692/) (2019)
- [3DSRnet: Video Super-resolution using 3D Convolutional Neural Networks](https://mlsanity.com/paper/1812.09079/) (2018)
- [Frame and Feature-Context Video Super-Resolution](https://mlsanity.com/paper/1909.13057/) (2019)
- [VESR-Net: The Winning Solution to Youku Video Enhancement and Super-Resolution Challenge](https://mlsanity.com/paper/2003.02115/) (2020)

## Abstract (arXiv)

Modern video super-resolution (VSR) systems based on convolutional neural networks (CNNs) require huge computational costs. The problem of feature redundancy is present in most models in many domains, but is rarely discussed in VSR. We experimentally observe that many features in VSR models are also similar to each other, so we propose to use "Ghost features" to reduce this redundancy. We also analyze the so-called "gradient disappearance" phenomenon generated by the conventional recurrent convolutional network (RNN) model, and combine the Ghost module with RNN to complete the modeling on time series. The current frame is used as input to the model together with the next frame, the output of the previous frame and the hidden state. Extensive experiments on several benchmark models and datasets show that the PSNR and SSIM of our proposed modality are improved to some extent. Some texture details in the video are also better preserved.