A collection of state-of-the-art video or single-image super-resolution architectures, reimplemented in tensorflow. (Now VEPSCN model has finally been added to Models, pretrained weights will be uploaded soon...)
The hyperlink directs to paper site, follows the official codes if the authors open sources.
All these models are implemented in ONE framework.
| Model | Published | Code* | VSR Included** | Keywords |
|---|---|---|---|---|
| SRCNN | ECCV14 | -, Keras | Y | Kaiming |
| RAISR | arXiv | - | N | Google, Pixel 3 |
| ESPCN | CVPR16 | -, Keras | Y | Real time |
| VDSR | CVPR16 | - | Y | Deep, Residual |
| DRCN | CVPR16 | - | Y | Recurrent |
| DRRN | CVPR17 | Caffe, PyTorch | Y | Recurrent |
| LapSRN | CVPR17 | Matlab | Y | Huber loss |
| EDSR | CVPR17 | - | Y | NTIRE17 Champion |
| SRGAN | CVPR17 | - | Y | 1st proposed GAN |
| VESPCN | CVPR17 | - | Y | VideoSR |
| MemNet | ICCV17 | Caffe | Y | |
| SRDenseNet | ICCV17 | -, PyTorch | T | Dense |
| SPMC | ICCV17 | Tensorflow | N | VideoSR |
| DnCNN | TIP17 | Matlab | Y | Denoise |
| DCSCN | arXiv | Tensorflow | Y | |
| IDN | CVPR18 | Caffe | Y | Fast |
| RDN | CVPR18 | Torch | Y | Deep, BI-BD-DN |
| SRMD | CVPR18 | Matlab | T | Denoise/Deblur/SR |
| DBPN | CVPR18 | PyTorch | Y | |
| ZSSR | CVPR18 | Tensorflow | N | Zero-shot |
| FRVSR | CVPR18 | T | VideoSR | |
| DUF | CVPR18 | Tensorflow | T | VideoSR |
| CARN | ECCV18 | PyTorch | Y | Fast |
| RCAN | ECCV18 | PyTorch | Y | Deep, BI-BD-DN |
| MSRN | ECCV18 | PyTorch | Y | |
| SRFeat | ECCV18 | Tensorflow | T | GAN |
| NLRN | NIPS18 | Tensorflow | T | Non-local, Recurrent |
| SRCliqueNet | NIPS18 | - | N | Wavelet |
| CBDNet | arXiv | Matlab | T | Blind-denoise |
*The 1st repo is by paper author.
**Y: included; N: non-included; T: under-testing.
(please contact me if any of links offend you or any one disabled)
| Name | Usage | # | Site | Comments |
|---|---|---|---|---|
| SET5 | Test | 5 | download | jbhuang0604 |
| SET14 | Test | 14 | download | jbhuang0604 |
| SunHay80 | Test | 80 | download | jbhuang0604 |
| Urban100 | Test | 100 | download | jbhuang0604 |
| VID4 | Test | 4 | download | 4 videos |
| BSD100 | Train | 300 | download | jbhuang0604 |
| BSD300 | Train/Val | 300 | download | - |
| BSD500 | Train/Val | 500 | download | - |
| 91-Image | Train | 91 | download | Yang |
| DIV2K | Train/Val | 900 | website | NTIRE17 |
| Waterloo | Train | 4741 | website | - |
| MCL-V | Train | 12 | website | 12 videos |
| GOPRO | Train/Val | 33 | website | 33 videos |
| CelebA | Train | 202599 | website | Human faces |
| Sintel | Train/Val | 35 | website | Optical flow |
| FlyingChairs | Train | 22872 | website | Optical flow |
| DND | Train/Val | 1000 | website | Real noisy photos |
Other open datasets: Kaggle ImageNet COCO
This package offers a training and data processing framework based on TF. What I made is a simple, easy-to-use framework without lots of encapulations and abstractions. Moreover, VSR can handle raw NV12/YUV as well as a sequence of images as inputs.
git clone https://github.com/loseall/VideoSuperResolution && cd VideoSuperResolution
pip install -e .To train/test/infer any model in VSR.Models, please see README. To write and train your own model via VSR, please see Docs.