• Stars
    star
    135
  • Rank 269,297 (Top 6 %)
  • Language
    Python
  • License
    Other
  • Created over 2 years ago
  • Updated over 1 year ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

[AAAI 2023] Exploring CLIP for Assessing the Look and Feel of Images

Exploring CLIP for Assessing the Look and Feel of Images (AAAI 2023)

Paper

visitors

Jianyi Wang, Kelvin C.K. Chan, Chen Change Loy

S-Lab, Nanyang Technological University

TODO

  • Colab demo
  • MMEditing update
  • Code release

Dependencies and Installation

The same as MMEditing, support the latest version 0.16.1.

# Create a conda environment and activate it
conda create -n clipiqa python=3.8 -y
conda activate clipiqa
# Install PyTorch following official instructions, e.g.
conda install pytorch=1.10 torchvision cudatoolkit=11.3 -c pytorch
# Install pre-built MMCV using MIM.
pip3 install openmim
mim install mmcv-full==1.5.0
# Install CLIP-IQA from the source code.
git clone [email protected]:IceClear/CLIP-IQA.git
cd CLIP-IQA
pip install -r requirements.txt
pip install -e .

Running Examples

Test CLIP-IQA on KonIQ-10k

python demo/clipiqa_koniq_demo.py

Test CLIP-IQA on Live-iWT

python demo/clipiqa_liveiwt_demo.py

Train CLIP-IQA+ on KonIQ-10k

# Support dist training as MMEditing
python tools/train.py configs/clipiqa/clipiqa_coop_koniq.py

Test CLIP-IQA+ on KonIQ-10k (Checkpoint)

python demo/clipiqa_koniq_demo.py --config configs/clipiqa/clipiqa_coop_koniq.py --checkpoint ./iter_80000.pth

[Note] You may change prompts for different datasets, please refer to config files for details.

[Note] For testing on a single image, please refer to here for details.

Demo

✨ Versatile Quality Assessment

✨ Demo for IQA on SPAQ

✨ Demo for Abstract Perception on AVA

For more evaluation, please refer to our paper for details.

Citation

If our work is useful for your research, please consider citing:

@inproceedings{wang2022exploring,
    author = {Wang, Jianyi and Chan, Kelvin CK and Loy, Chen Change},
    title = {Exploring CLIP for Assessing the Look and Feel of Images},
    booktitle = {AAAI},
    year = {2023}
}

License

This project is licensed under NTU S-Lab License 1.0. Redistribution and use should follow this license.

Acknowledgement

This project is based on MMEditing and CLIP. Thanks for their awesome works.

Contact

If you have any question, please feel free to reach me out at [email protected].