XOS>> Awesome-Super-Resolution>> 返回
项目作者： kozistr

项目描述 ：
lots of single image super resolution model implementations in tensorflow
高级语言： Python
项目地址: git://github.com/kozistr/Awesome-Super-Resolution.git
创建时间： 2019-06-16T09:41:31Z
项目社区：https://github.com/kozistr/Awesome-Super-Resolution
开源协议：MIT License
下载


Awesome Super Resolution

Lots of SISR (Single Image Super Resolution) implementations in tensorflow maybe w/ pre-trained model!

maybe later, this repo could be supported via pip package.

Currently, Work-In-Progress

Total alerts
Language grade: Python
License: MIT

Usage

PIP

  1. [not available yet :(]

Download

  1. $ git clone https://github.com/kozistr/Awesome-Super-Resolution
  2. $ cd ./Awesome-Super-Resolution

Dependency Install

  1. $ pip3 install -r ./requirements.txt

Train / Eval / Inference

  1. $ python3 train.py [w/ some parameters]
  2. $ python3 eval.py [w/ some parameters]
  3. $ python3 inference.py [w/ some parameters]

DataSets

  • DIV2K
  • Flicker2K
  • Set*

Repo Tree

  1. │
  2. ├── assets (dir, images used in readme.md)
  3. ├── models
  4. │    ├── vgg16.py (VGG19 model loader)
  5. │    ├── vgg19.py (VGG16 model loader)
  6. │    ├── xxx (dir, model name)
  7. │    │     ├── logs      (tensorboard logs)
  8. │    │     ├── config.py (configurations)
  9. │    │     ├── model.py  (model script)
  10. │    │     └── readme.md (results & explains)
  11. │    └── ... (dir, model name)
  12. │          └── ...
  13. ├── train.py       (trainer)
  14. ├── eval.py        (evaluator)
  15. ├── inference.py   (inferencer)
  16. ├── ops.py         (useful tf operators)
  17. ├── utils.py       (useful image utilities)
  18. ├── metrics.py     (metrics for evaluating SR Model)
  19. ├── dataloader.py  (dataset loader / feeder)
  20. └── readme.py      (readme)

Papers & Codes

Name Summary Paper Code
2015
SRCNN Image Super-Resolution Using Deep Convolutional Networks [arXiv] [code]
2016
SRGAN Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network [arXiv] [code]
FSRGAN Accelerating the Super-Resolution Convolutional Neural Network [arXiv] [code]
EnhanceNet Single Image Super-Resolution Through Automated Texture Synthesis [arXiv] [code]
2017
LapSRN Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution [arXiv] [code]
EDSR Enhanced Deep Residual Networks for Single Image Super-Resolution [arXiv] [code]
2018
RCAN Image Super-Resolution Using Very Deep Residual Channel Attention Networks [arXiv] [code]
ESRGAN Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution [arXiv] [code]
FEQE Fast and Efficient Image Quality Enhancement via Desubpixel Convolutional Neural Networks [ECCV] [code]
IDN Fast and Accurate Single Image Super-Resolution via Information Distillation Network [ECCV] [code]
2019
NNTSR Image Super-Resolution by Neural Texture Transfer [arXiv] [code]

Pre-Trained Models

It’s on the plan, but, because of the lack of hardware resources, it can be.

To-Be-Done

  1. TBD

ETC

Any suggestions and PRs and issues are WELCOME :)

Author

HyeongChan Kim / @kozistr