A collection of state-of-the-art video or single-image super-resolution architectures, reimplemented in tensorflow. (currently no video models...)
The hyperlink directs to paper site, follows the official codes if the authors open sources.
-
Classic
-
CVPR 2016
-
CVPR 2017
- Deep Recursive Residual Network: DRRN https://github.com/tyshiwo/DRRN_CVPR17
- Deep Laplacian Pyramid Networks: LapSRN https://github.com/phoenix104104/LapSRN
- Enhanced Deep Residual Networks: EDSR
-
ICCV 2017
- Memory Network: MemNet https://github.com/tyshiwo/MemNet
-
CVPR 2018
- Information Distillation Network: IDN https://github.com/Zheng222/IDN-Caffe
- Residual Dense Network: RDN https://github.com/yulunzhang/RDN
- Super-Resolution Network for Multiple Degradations: SRMD https://github.com/cszn/SRMD
- Deep Back-Projection Networks: DBPN https://github.com/alterzero/DBPN-Pytorch
- Zero-Shot Super-Resolution: ZSSR https://github.com/assafshocher/ZSSR
-
Others
- DNCNN (This is for denoise) https://github.com/cszn/DnCNN
- Deep CNN with Skip Connection: DCSCN https://github.com/jiny2001/dcscn-super-resolution
All these models are implemented in ONE framework.
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 .
Require: tensorflow-gpu, numpy, PIL
Dataset
offers manipulation of virtual images. Virtual means the images can be either a single png file or a list of jpeg files as a sequence of images. One need to provide a JSON config file, see here.Loader
offersBatchLoader
object to generate image patches with HR and LR pairsVirtualFile
is internally used object to depict the file object
Environment
offers a simple framework specific to super resolution. See examples for instance. And see Environment.py for details.Callbacks
offers a collection of callback functions used inEnvironment.fit
,Environment.test
andEnvironment.predict
SuperResolution
is the parent object to all models
Offers a collection of implementations for recent papers and research works.
To avoid storing a mess of images in codebase, I offer you links to widely used database and a configuration file to describe your own datasets. For config file, see here as a sample, and here for details.
Above links are from jbhuang0604
You can either train via Environment
object or via your own script.
You can also use pre-made script to train the models in VSR package.
See readme for details.
- MemNet
- ZSSR
- SRMD