Home

Awesome

I2IQA

This is the official repo of the paper PKU-I2IQA: An Image-to-Image Quality Assessment Database for AI Generated Images:

@misc{yuan2023pkui2iqa,
    title={PKU-I2IQA: An Image-to-Image Quality Assessment Database for AI Generated Images}, 
    author={Jiquan Yuan and Xinyan Cao and Changjin Li and Fanyi Yang and Jinlong Lin and Xixin Cao},
    year={2023},
    eprint={2311.15556},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}
<hr />

Abstract: As image generation technology advances, AI-based image generation has been applied in various fields and Artificial Intelligence Generated Content (AIGC) has garnered widespread attention. However, the development of AI-based image generative models also brings new problems and challenges. A significant challenge is that AI-generated images (AIGI) may exhibit unique distortions compared to natural images, and not all generated images meet the requirements of the real world. Therefore, it is of great significance to evaluate AIGIs more comprehensively. Although previous work has established several human perception-based AIGC image quality assessment (AIGCIQA) databases for text-generated images, the AI image generation technology includes scenarios like text-to-image and image-to-image, and assessing only the images generated by text-to-image models is insufficient. To address this issue, we establish a human perception-based image-to-image AIGCIQA database, named PKU-I2IQA. We conduct a well-organized subjective experiment to collect quality labels for AIGIs and then conduct a comprehensive analysis of the PKU-I2IQA database. Furthermore, we propose two benchmark models: NR-AIGCIQA based on the no-reference image quality assessment method and FR-AIGCIQA based on the full-reference image quality assessment method. Finally, leveraging this database, we conduct benchmark experiments and compare the performance of the proposed benchmark models.

<hr />

Sampled images

Various scenes and styles of images sampled from the PKU-I2IQA database, generated by Midjourney and Stable Diffusion V1.5.

<img src="./Pic/1.png" width="600" height="500">

NR-AIGCIQA

<img src="./Pic/5.png" width="600" height="170">

FR-AIGCIQA

<img src="./Pic/6.png" width="600" height="300">

Pre-trained visual backbone

For feature extraction from input images, we selected several backbone network models pre-trained on the ImageNet dataset, including:

Database

The constructed PKU-I2IQA database can be accessed using the links below. Download PKU-I2IQA database: 1.[百度网盘 (提取码：i2ia)]. 2.[Google Drive]

Training Codes

For how to train the NR-AIGCIQA/FR-AIGCIQA model on the I2IQA dataset, please refer to AIGIQA4K.

Contact

If you have any question, please contact yuanjiquan@stu.pku.edu.cn