346-promptir-prompting-for-all-in-one-blind-image-restoration

https://github.com/szu-advtech-2024/346-promptir-prompting-for-all-in-one-blind-image-restoration

Science Score: 31.0%

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
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (5.9%) to scientific vocabulary

Last synced: 9 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 over 1 year ago · Last pushed over 1 year ago

Metadata Files

Citation

https://github.com/SZU-AdvTech-2024/346-PromptIR-Prompting-for-All-in-One-Blind-Image-Restoration/blob/main/

##### I. This reproduction project mainly refers to : [Github](https://github.com/va1shn9v/PromptIR)
Hint: The original PromptIR project provides a relatively bloated `env.yml` for configuring the environment, which prones to failure. We recommend the following approach instead:
1. Install appropriate `torch, torchvision` and `pytorch-lightning` in your environment, which are the main dependencies for running the project. 
For our environment (which requires CUDA>=11.1):
    ```
    conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 pytorch-cuda=11.6 -c pytorch -c nvidia
    conda install lightning -c conda-forge
    ```
1. Try running the project and install any missing dependencies as prompted using `pip install` or `conda install`. In our practice, the following requirements need to be installed: `wandb, einops, matplotlib, scikit-image`.
This method can ensure to the greatest extent that the environment is correctly configured to suit your own device.


##### II. The DAVIS 2016 dataset can be downloaded from[DAVIS 2016](https://davischallenge.org/davis2016/code.html)
To create compressed video frames using ffmpeg, please refer to `ffmpeg.txt`

Owner

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

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

Citation (citation.txt)

@inproceedings{REPO346,
    author = "Potlapalli, Vaishnav and Zamir, Syed Waqas and Khan, Salman and Khan, Fahad",
    booktitle = "Thirty-seventh Conference on Neural Information Processing Systems",
    title = "{PromptIR: Prompting for All-in-One Image Restoration}",
    year = "2023"
}

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science