kozistr / Rcan Tensorflow
Licence: mit
Image Super-Resolution Using Very Deep Residual Channel Attention Networks Implementation in Tensorflow
Stars: ✭ 43
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Rcan Tensorflow
Ntire2017
Torch implementation of "Enhanced Deep Residual Networks for Single Image Super-Resolution"
Stars: ✭ 554 (+1188.37%)
Mutual labels: super-resolution
Srgan Tensorflow
Tensorflow implementation of the SRGAN algorithm for single image super-resolution
Stars: ✭ 754 (+1653.49%)
Mutual labels: super-resolution
Super Resolution cnn
Implementation of 'Image Super-Resolution using Deep Convolutional Network'
Stars: ✭ 27 (-37.21%)
Mutual labels: super-resolution
Wdsr ntire2018
Code of our winning entry to NTIRE super-resolution challenge, CVPR 2018
Stars: ✭ 570 (+1225.58%)
Mutual labels: super-resolution
Dpsr
Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels (CVPR, 2019) (PyTorch)
Stars: ✭ 738 (+1616.28%)
Mutual labels: super-resolution
Pytorch Implemented Deep Sr Itm
A Pytorch implemented Deep SR-ITM (ICCV2019)
Stars: ✭ 23 (-46.51%)
Mutual labels: super-resolution
Usrnet
Deep Unfolding Network for Image Super-Resolution (CVPR, 2020) (PyTorch)
Stars: ✭ 493 (+1046.51%)
Mutual labels: super-resolution
Hyperspectral Image Spatial Super Resolution Via 3d Full Convolutional Neural Network
Hyperspectral Image Spatial Super-Resolution via 3D-Full-Convolutional-Neural-Network
Stars: ✭ 41 (-4.65%)
Mutual labels: super-resolution
Super Resolution.benckmark
Benchmark and resources for single super-resolution algorithms
Stars: ✭ 745 (+1632.56%)
Mutual labels: super-resolution
Dncnn
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (TIP, 2017)
Stars: ✭ 912 (+2020.93%)
Mutual labels: super-resolution
Dcscn Super Resolution
A tensorflow implementation of "Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network", a deep learning based Single-Image Super-Resolution (SISR) model.
Stars: ✭ 611 (+1320.93%)
Mutual labels: super-resolution
Kair
Image Restoration Toolbox (PyTorch). Training and testing codes for USRNet, DnCNN, FFDNet, SRMD, DPSR, ESRGAN
Stars: ✭ 677 (+1474.42%)
Mutual labels: super-resolution
Scn
Scale-wise Convolution for Image Restoration
Stars: ✭ 26 (-39.53%)
Mutual labels: super-resolution
Zooming Slow Mo Cvpr 2020
Fast and Accurate One-Stage Space-Time Video Super-Resolution (accepted in CVPR 2020)
Stars: ✭ 555 (+1190.7%)
Mutual labels: super-resolution
Super Resolution
Tensorflow 2.x based implementation of EDSR, WDSR and SRGAN for single image super-resolution
Stars: ✭ 952 (+2113.95%)
Mutual labels: super-resolution
Srflow
Official SRFlow training code: Super-Resolution using Normalizing Flow in PyTorch
Stars: ✭ 537 (+1148.84%)
Mutual labels: super-resolution
Neuralsuperresolution
Real-time video quality improvement for applications such as video-chat using Perceptual Losses
Stars: ✭ 18 (-58.14%)
Mutual labels: super-resolution
Jsi Gan
Official repository of JSI-GAN (Accepted at AAAI 2020).
Stars: ✭ 42 (-2.33%)
Mutual labels: super-resolution
Tensorflow Srgan
Tensorflow implementation of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network" (Ledig et al. 2017)
Stars: ✭ 33 (-23.26%)
Mutual labels: super-resolution
Training extensions
Trainable models and NN optimization tools
Stars: ✭ 857 (+1893.02%)
Mutual labels: super-resolution
rcan-tensorflow
Image Super-Resolution Using Very Deep Residual Channel Attention Networks Implementation in Tensorflow
Introduction
This repo contains my implementation of RCAN (Residual Channel Attention Networks).
Here're the proposed architectures in the paper.
-
Channel Attention (CA)
-
Residual Channel Attention Block (RCAB)
-
Residual Channel Attention Network (RCAN), Residual Group (GP)
All images got from the paper
Dependencies
- Python
- Tensorflow 1.x
- tqdm
- h5py
- scipy
- cv2
DataSet
| DataSet | LR | HR |
|---|---|---|
| DIV2K | 800 (192x192) | 800 (768x768) |
Usage
training
# hyper-paramters in config.py, you can edit them!
$ python3 train.py --data_from [img or h5]
testing
$ python3 test.py --src_image sample.png --dst_image sample-upscaled.png
Results
- OOM on my machine :(... I can't test my code, but maybe code runs fine.
| Example\Resolution | 192x192x3 image (sample) | 768x768x3 image (generated) |
|---|---|---|
| Example1 (X4 scaled) |  |
 |
To-Do
- None
Author
HyeongChan Kim / @kozistr
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].