champion-solution-for-cvpr-ntire-2024-quality-assessment-on-aigc's Introduction

Champion-Solution-for-CVPR-NTIRE-2024-Quality-Assessment-on-AIGC Quality Assessment for AI-Generated Content - Track 1: Image

Beijing University of Posts and Telecommunications.
Beijing Xiaomi Mobile Software Co., Ltd.

Introduction

The official repo of AIGC Image Quality Assessment via Image-Prompt Correspondence. (CVPRW2024, the first place in the image track of the NTIRE 2024 Quality Assessment for AI-Generated Content challenge).

Environment Installation

torch 1.8+
torchvision
Python 3
pip install ftfy regex tqdm
pip install git+https://github.com/openai/CLIP.git

Data Preparation

Download the competition test dataset from the specified website and unzip it into the "./data/AIGCQA-30K-Image/test" directory.

Trained Datasets

Download AGIQA-1K, AGIQA-3K, AIGCIQA2023 and AIGCQA-30K-Image datasets and unzip them into the "./data" directory.

Training and Testing

After preparing the code environment and downloading the data, run the following codes to train and test model.

#AIGCQA-30K-Image
python train_aigcqa30k.py
#AGIQA-1K
python train_aigc_agiqa1k.py
#AGIQA-3K
python train_aigc_agiqa3k.py
#AIGCIQA2023
python train_aigc_aigciqa2023.py

For AIGCQA-30-Image dataset, run the following codes to get val and test output.

AIGC_DB_AIGCQA30K_VAL.py
AIGC_DB_AIGCQA30K_TEST.py

Citation

If you find our work useful in your research, please consider citing our paper:

@InProceedings{Peng_2024_CVPR,
    author    = {Peng, Fei and Fu, Huiyuan and Ming, Anlong and Wang, Chuanming and Ma, Huadong and He, Shuai and Dou, Zifei and Chen, Shu},
    title     = {AIGC Image Quality Assessment via Image-Prompt Correspondence},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
    month     = {June},
    year      = {2024},
    pages     = {6432-6441}
}

Our other works:

"Thinking Image Color Aesthetics Assessment: Models, Datasets and Benchmarks.", [pdf] [code], ICCV 2023.
"EAT: An Enhancer for Aesthetics-Oriented Transformers.", [pdf] [code] ACMMM 2023.
"Rethinking Image Aesthetics Assessment: Models, Datasets and Benchmarks.", [pdf] [code] IJCAI 2022.

champion-solution-for-cvpr-ntire-2024-quality-assessment-on-aigc's People

Contributors

Stargazers

Watchers

champion-solution-for-cvpr-ntire-2024-quality-assessment-on-aigc's Issues

dataset

Hi,contributors,
I read the article about the competition. You are very excellent. I would like to ask where to download the training and verification data and test data of the competition pictures and videos tracks . I did not see them on the official website. Could you please give me the website address? I would like to use it for my own academic research. I look forward to your reply. Thank you.

what is the difference between these two models?There is another running script in this document. What is the difference between it and the script in the original warehouse?

Hello, I used the AIGC_DB_AIGCQA30K_TEST.py file in the github repository and the AIGC_DB_prompt_final.py in the url download link you shared, and the results on the test set are different:

Looking at the code, I found that AIGC_DB_prompt_final.py uses the above two models at the same time and merges the results of the two models. What is the purpose of this? What is the difference between the two reasoning methods and the two models? Which of the two reasoning methods is more accurate?

woshidandan / champion-solution-for-cvpr-ntire-2024-quality-assessment-on-aigc Goto Github PK