This repo is built for paper: Video Super Resolution Based on Deep Learning: A Comprehensive Survey【paper】
Citing this work
If this repository is helpful to you, please cite our survey.
@article{liu2022video,
title={Video super-resolution based on deep learning: a comprehensive survey},
author={Liu, Hongying and Ruan, Zhubo and Zhao, Peng and Dong, Chao and Shang, Fanhua and Liu, Yuanyuan and Yang, Linlin and Timofte, Radu},
journal={Artificial Intelligence Review},
pages={1--55},
year={2022},
publisher={Springer}
}
@article{liu2020video,
title={Video super resolution based on deep learning: A comprehensive survey},
author={Liu, Hongying and Ruan, Zhubo and Zhao, Peng and Dong, Chao and Shang, Fanhua and Liu, Yuanyuan and Yang, Linlin},
journal={arXiv preprint arXiv:2007.12928},
year={2020}
}
🔥 (citations > 200)
| Paper | Model | Code | Published |
|---|---|---|---|
| Video Super-Resolution via Deep Draft-Ensemble Learning [Project Page] 🔥 | Deep-DE | MATLAB | ICCV2015 |
| Video Super-Resolution With Convolutional Neural Networks 🔥 | VSRnet | PyTorch | TCI2016 |
| Real-Time Video Super-Resolution With Spatio-Temporal Networks and Motion Compensation 🔥 | VESPCN | PyTorch, TensorFlow | CVPR2017, arXiv |
| Detail-Revealing Deep Video Super-Resolution 🔥 | DRVSR | TensorFlow | ICCV2017, arXiv |
| Robust Video Super-Resolution with Learned Temporal Dynamics | RVSR | / | ICCV2017, arXiv |
| Frame-Recurrent Video Super-Resolution 🔥 | FRVSR | GitHub | CVPR2018, arXiv |
| Spatio-Temporal Transformer Network for Video Restoration | STTN | PyTorch | ECCV2018, arXiv |
| Learning for Video Super-Resolution Through HR Optical Flow Estimation (ACCV), Deep Video Super-Resolution using HR Optical Flow Estimation (TIP) | SOFVSR | PyTorch | ACCV2018, TIP2020 |
| Video Enhancement with Task-Oriented Flow 🔥 | TOFlow | PyTorch | IJCV2019, arXiv |
| Multi-Memory Convolutional Neural Network for Video Super-Resolution | MMCNN | TensorFlow | TIP2019 |
| MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement | MEMC-Net | PyTorch | TPAMI2021, arXiv |
| Video Super-Resolution Using Non-Simultaneous Fully Recurrent Convolutional Network | RRCN | / | TIP2019 |
| Real-time video super-resolution via motion convolution kernel estimation | RTVSR | / | NEUCOM |
| Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation [Project Page] | TecoGAN | TensorFlow, PyTorch | TG2020, arXiv |
| MultiBoot VSR: Multi-Stage Multi-Reference Bootstrapping for Video Super-Resolution | MultiBoot VSR | / | CVPRW2019 |
| MuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution | MuCAN | PyTorch | ECCV2020, arXiv |
| BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond [Project Page] | BasicVSR | PyTorch | CVPR2021, arXiv |
| Paper | Model | Code | Published |
|---|---|---|---|
| EDVR: Video Restoration With Enhanced Deformable Convolutional Networks [Project Page] 🔥 | EDVR | PyTorch | CVPR2019, arXiv |
| Deformable Non-Local Network for Video Super-Resolution | DNLN | PyTorch | ACCESS2019 |
| TDAN: Temporally-Deformable Alignment Network for Video Super-Resolution | TDAN | PyTorch | CVPR2020, arXiv |
| Deformable 3D Convolution for Video Super-Resolution | D3Dnet | PyTorch | SPL2020, arXiv |
| VESR-Net: The Winning Solution to Youku Video Enhancement and Super-Resolution Challenge | VESR-Net | / | arXiv |
| Paper | Model | Code | Published |
|---|---|---|---|
| Generative Adversarial Networks and Perceptual Losses for Video Super-Resolution | VSRResFeatGAN | / | TIP2019, arXiv |
| Frame and Feature-Context Video Super-Resolution | FFCVSR | TensorFlow | AAAI2019 |
| Paper | Model | Code | Published |
|---|---|---|---|
| Deep Video Super-Resolution Network Using Dynamic Upsampling FiltersWithout Explicit Motion Compensation 🔥 | DUF | TensorFlow | CVPR2018 |
| Fast Spatio-Temporal Residual Network for Video Super-Resolution | FSTRN | TensorFlow | CVPR2019, arXiv |
| 3DSRnet: Video Super-resolution using 3D Convolutional Neural Networks | 3DSRnet | MATLAB | ICIP2019, arXiv |
| Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsampling | DSMC | PyTorch | AAAI2021, arXiv |
| Paper | Model | Code | Published |
|---|---|---|---|
| Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution(NeurIPS) Video Super-Resolution via Bidirectional Recurrent Convolutional Networks (TPAMI) |
BRCN | MATLAB | NeurIPS2015, TPAMI2017 |
| Building an End-to-End Spatial-Temporal Convolutional Network for Video Super-Resolution | STCN | / | AAAI2017 |
| Residual Invertible Spatio-Temporal Network for Video Super-Resolution | RISTN | PyTorch | AAAI2019 |
| Efficient Video Super-Resolution through Recurrent Latent Space Propagation | RLSP | PyTorch | ICCVW2019, arXiv |
| Video Super-Resolution with Recurrent Structure-Detail Network | RSDN | PyTorch | ECCV2020, arXiv |
| Paper | Model | Code | Published |
|---|---|---|---|
| Progressive Fusion Video Super-Resolution Network via Exploiting Non-Local Spatio-Temporal Correlations | PFNL | TensorFlow | ICCV2019 |
| Paper | Model | Code | Published |
|---|---|---|---|
| Recurrent Back-Projection Network for Video Super-Resolution [[Project Page]](Project page) | RBPN | PyTorch | CVPR2019, arXiv |
| Space-Time-Aware Multi-Resolution Video Enhancement | STARnet | PyTorch | CVPR2020, arXiv |
| Video super-resolution via dense non-local spatial-temporal convolutional network | DNSTNet | / | NEUCOM2020 |
Some new methods that were not categorized.
| Paper | Model | Code | Published |
|---|---|---|---|
| Omniscient Video Super-Resolution | OVSR | PyTorch | ICCV2021 |
| Learning interlaced sparse Sinkhorn matching network for video super-resolution | ISSM | / | PATCOG2021 |
| MEGAN: Memory Enhanced Graph Attention Network for Space-Time Video Super-Resolution | MEGAN | / | WACV2022 |
| Plug-and-Play video super-resolution using edge-preserving filtering | / | / | CVIU2022 |
| Video super-resolution using a hierarchical recurrent multireceptive-field integration network | RMRIN | / | DSP2021 |
| Improved EDVR Model for Robust and Efficient Video Super-Resolution | / | / | WACV2022 |
| Video super-resolution network using detail component extraction and optical flow enhancement algorithm | / | / | Appl Intell2022 |
| Deeply feature fused video super-resolution network using temporal grouping | / | / | Supercomput2022 |
| Frame Attention Recurrent Back-Projection Network for Accurate Video Super-Resolution | / | / | ICCE2022 |
| Semi-Supervised Super-Resolution | / | / | arXiv |
| STDAN: Deformable Attention Network for Space-Time Video Super-Resolution | STDAN | / | arXiv |
| Fast Online Video Super-Resolution with Deformable Attention Pyramid | DAP-128 | / | arXiv |
| Self-Supervised Deep Blind Video Super-Resolution | / | PyTorch | arXiv |
| Video Super-Resolution Transformer | VSRT | PyTorch | arXiv |
| VRT: A Video Restoration Transformer | VRT | PyTorch | arXiv |