AIGCIQA2023: A Large-scale Image Quality Assessment Database for AI Generated Images: from the Perspectives of Quality, Authenticity and Correspondence
This provides a new benchmark for evaluating AI-generated images, addressing a gap in the field, but it is incremental as it builds on existing IQA methods by applying them to a new dataset.
The authors tackled the problem of understanding human visual preferences for AI-generated images by creating a large-scale image quality assessment database called AIGCIQA2023, which includes over 2000 images from 6 text-to-image models and subjective ratings for quality, authenticity, and correspondence, and they benchmarked several IQA metrics on this database.
In this paper, in order to get a better understanding of the human visual preferences for AIGIs, a large-scale IQA database for AIGC is established, which is named as AIGCIQA2023. We first generate over 2000 images based on 6 state-of-the-art text-to-image generation models using 100 prompts. Based on these images, a well-organized subjective experiment is conducted to assess the human visual preferences for each image from three perspectives including quality, authenticity and correspondence. Finally, based on this large-scale database, we conduct a benchmark experiment to evaluate the performance of several state-of-the-art IQA metrics on our constructed database.