DASR

KO | EN

gitlite — search

#javascript #python #react #llm #go #android #machine-learning #awesome #kubernetes #awesome-list #vue #security #mcp #openai

(★ 422)

[CVPR 2021] Unsupervised Degradation Representation Learning for Blind Super-Resolution

파일 탐색기

최종 버전 다운로드 (.zip)

- __init__.py
- __init__.pyc
- benchmark.py
- common.py
- df2k.py
- multiscalesrdata.py
- fig.1.png
- fig.2.png
- fig.5.png
- fig.6.png
- fig.7.png
- fig.III.png
- fig.VII.png
- tab2.png
- tab3.png
- __init__.py
- adversarial.py
- discriminator.py
- vgg.py
- __init__.py
- builder.py
- __init__.py
- blindsr.py
- common.py
- __init__.py
- util.py
dataloader.py
LICENSE
main.py
main.sh
option.py
quick_test.py
quick_test.sh
README.md
template.py
test.py
test.sh
trainer.py
utility.py

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# DASR
Pytorch implementation of "Unsupervised Degradation Representation Learning for Blind Super-Resolution", CVPR 2021

[[arXiv]](http://arxiv.org/pdf/2104.00416) [[CVF]](https://openaccess.thecvf.com/content/CVPR2021/papers/Wang_Unsupervised_Degradation_Representation_Learning_for_Blind_Super-Resolution_CVPR_2021_paper.pdf) [[Supp]](https://openaccess.thecvf.com/content/CVPR2021/supplemental/Wang_Unsupervised_Degradation_Representation_CVPR_2021_supplemental.pdf)

## Overview

## Requirements
- Python 3.6
- PyTorch == 1.1.0
- numpy
- skimage
- imageio
- matplotlib
- cv2

## Train
### 1. Prepare training data

1.1 Download the [DIV2K](https://data.vision.ee.ethz.ch/cvl/DIV2K/)  dataset and the [Flickr2K](http://cv.snu.ac.kr/research/EDSR/Flickr2K.tar) dataset.

1.2 Combine the HR images from these two datasets in `your_data_path/DF2K/HR` to build the DF2K dataset.

### 2. Begin to train
Run `./main.sh` to train on the DF2K dataset. Please update `dir_data` in the bash file as `your_data_path`.

## Test
### 1. Prepare test data 
Download [benchmark datasets](https://github.com/xinntao/BasicSR/blob/a19aac61b277f64be050cef7fe578a121d944a0e/docs/Datasets.md) (e.g., Set5, Set14 and other test sets) and prepare HR/LR images in `your_data_path/benchmark`.

### 2. Begin to test
Run `./test.sh` to test on benchmark datasets. Please update `dir_data` in the bash file as `your_data_path`.

## Quick Test on An LR Image
Run `./quick_test.sh` to test on an LR image. Please update `img_dir` in the bash file as `your_img_path`.

## Visualization of Degradation Representations
 <img src="Figs/fig.6.png" width="50%">

## Comparative Results
### Noise-Free Degradations with Isotropic Gaussian Kernels

### General Degradations with Anisotropic Gaussian Kernels and Noises
 <img src="Figs/tab3.png" width="100%">

### Unseen Degradations

### Real Degradations (AIM real-world SR challenge)

## Citation
```
@InProceedings{Wang2021Unsupervised,
  author    = {Wang, Longguang and Wang, Yingqian and Dong, Xiaoyu and Xu, Qingyu and Yang, Jungang and An, Wei and Guo, Yulan},
  title     = {Unsupervised Degradation Representation Learning for Blind Super-Resolution},
  booktitle = {CVPR},
  year      = {2021},
}
```

## Acknowledgements
This code is built on [EDSR (PyTorch)](https://github.com/thstkdgus35/EDSR-PyTorch), [IKC](https://github.com/yuanjunchai/IKC) and [MoCo](https://github.com/facebookresearch/moco). We thank the authors for sharing the codes.

DASR

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

DASR

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README