AI text-to-image generators: an evaluation from a photographic perspective

TU Ilmenau / Audiovisual Technology Group
TU Ilmenau / Audiovisual Technology Group

Article evaluating AI-generated images from a photographic perspective published in IEEE Access:

Steve Goering, Rakesh Rao Ramachandra Rao, Rasmus Merten, and Alexander Raake "Analysis of Appeal for realistic AI-generated Photos."

AI-generated images have gained in popularity in recent years. This has led to several new AI generators, which may produce realistic, funny, and impressive images using a simple text prompt. DALL-E-2, Midjourney, and Craiyon are a few examples of the mentioned approaches. In general, it can be seen that the quality, realism, and appeal of the images vary depending on the used approach. Therefore, in this paper, we analyze to what extent such AI-generated images are realistic or of high appeal from a more photographic point of view and how users perceive them.

To evaluate the appeal of several state-of-the-art AI generators, we develop a dataset consisting of 27 different text prompts. Using these prompts we generated a total of 135 images with five different AI-Text-To-Image generators. The evaluation is based on an online subjective study and the results are compared with state-of-the-art image quality models and features.

The results indicate that some of the included generators are able to produce realistic and highly appealing images. However, this depends on the approach and text prompt to a large extent. The dataset and evaluation of this paper are made publicly available for reproducibility, following an Open Science approach.

Link: https://ieeexplore.ieee.org/document/10103686

DOI: https://doi.org/10.1109/ACCESS.2023.3267968