144-a-dynamic-kernel-prior-model-for-unsupervised-blind-image-super-resolution

https://github.com/szu-advtech-2024/144-a-dynamic-kernel-prior-model-for-unsupervised-blind-image-super-resolution

Science Score: 41.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
○
.zenodo.json file
○
DOI references
✓
Academic publication links
Links to: arxiv.org
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (7.1%) to scientific vocabulary

Last synced: 7 months ago · JSON representation ·

Repository

Basic Info

Host: GitHub
Owner: SZU-AdvTech-2024
Default Branch: main
Size: 0 Bytes

Statistics

Stars: 0
Watchers: 0
Forks: 0
Open Issues: 0
Releases: 0

Created about 1 year ago · Last pushed about 1 year ago

Metadata Files

Citation

https://github.com/SZU-AdvTech-2024/144-A-Dynamic-Kernel-Prior-Model-for-Unsupervised-Blind-Image-Super-Resolution/blob/main/

# A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution (DKP), CVPR2024

This repository is the official PyTorch implementation of DKP to Blind Super-Resolution 
([arXiv](https://arxiv.org/abs/2404.15620), [supp](https://github.com/XYLGroup/DKP)).

## Requirements

- pip install numpy torch blobfile tqdm pyYaml pillow    # e.g. torch 1.7.1+cu110.

### Pre-Trained Models for DiffDKP

To restore general images, download this [model](https://openaipublic.blob.core.windows.net/diffusion/jul-2021/256x256_diffusion.pt)(from [guided-diffusion](https://github.com/openai/guided-diffusion)) and put it into `DiffDKP/data/pretrained/`.

```
wget https://openaipublic.blob.core.windows.net/diffusion/jul-2021/256x256_diffusion.pt
wget https://openaipublic.blob.core.windows.net/diffusion/jul-2021/256x256_classifier.pt
```

Note that the pre-trained models are only used for DiffDKP, DIPDKP is processed without pre-trained models.

## Quick Run DIPDKP

To run the code without preparing data, run this command:

```bash
cd DIPDKP/DIPDKP
python main.py
```

## Quick Run DiffDKP

To run the code without preparing data, run this command:

```bash
cd DiffDKP
python main.py
```

---

## Data Preparation for DIPDKP

To prepare testing data, please organize images as `data/datasets/Set5/HR/baby.png`, and run this command:

```bash
cd DIPDKP/data
python prepare_dataset.py --model DIPDKP --sf 2 --dataset Set5
```

## Data Preparation for DiffDKP

To prepare testing data, please organize images as `data/datasets/deblur/Set5/HR_256/baby.png`, and run this command:

```bash
cd DiffDKP/data
python prepare_dataset.py --model DIPDKP --sf 2 --dataset Set5
```

Commonly used datasets can be downloaded [here](https://github.com/xinntao/BasicSR/blob/master/docs/DatasetPreparation.md#common-image-sr-datasets).



#

Owner

Name: SZU-AdvTech-2024
Login: SZU-AdvTech-2024
Kind: organization

Repositories: 1
Profile: https://github.com/SZU-AdvTech-2024

Citation (citation.txt)

@inproceedings{REPO144,
    author = "Yang, Zhixiong and Xia, Jingyuan and Li, Shengxi and Huang, Xinghua and Zhang, Shuanghui and Liu, Zhen and Fu, Yaowen and Liu, Yongxiang",
    booktitle = "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
    pages = "26046--26056",
    title = "{A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution}",
    year = "2024"
}

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science