AGIAA-2K: A Fine-grained Dataset for Aesthetic and Alignment Evaluation of AI-Generated Images
Bo Hu, Nanxiang Li, Lihuo He, Wen Lu, Leida Li, Xinbo Gao
Abstract
With the advancement of AI-generated content technologies, AI-generated images (AGIs) have become increasingly influential in artistic creation and visual communication. However, the aesthetic quality of AGIs varies significantly due to technical limitations and the influence of user input, underscoring the urgent need for systematic aesthetic evaluation of AGIs. In addition, it is difficult to ensure the consistency of text-to-image, which compresses the application space of AGIs. To address these issues, a fine-grained dataset for Aesthetic and Alignment evaluation of AGIs (AGIAA-2K) is presented. This dataset contains 2,064 images generated using 172 well-designed prompts across six different AGI models, with each image annotated based on the subjective experiment. Then, the rationality of the dataset is verified by data analysis. Finally, the performances of the existing algorithms are evaluated in terms of image aesthetic assessment and text-to-image alignment of AGIs. The results demonstrate that these algorithms cannot effectively evaluate these two aspects. The AGIAA-2K is available at https://github.com/BoHu90/AGIAA-2K.
BibTeX
@inproceedings{icassp2025_agiaa2kafinegrai,
title = {AGIAA-2K: A Fine-grained Dataset for Aesthetic and Alignment Evaluation of AI-Generated Images},
author = {Bo Hu and Nanxiang Li and Lihuo He and Wen Lu and Leida Li and Xinbo Gao},
booktitle = {ICASSP 2025},
year = {2025}
}