AI-Generated Image Quality Assessment Based on Task-Specific Prompt and Multi-Granularity Similarity

TL;DR

This paper introduces TSP-MGS, a novel AI-generated image quality assessment method that uses task-specific prompts and multi-granularity similarity measures to evaluate perception and alignment quality more accurately.

Contribution

It proposes a new assessment framework that distinguishes perception and alignment tasks using tailored prompts and multi-level similarity metrics.

Findings

TSP-MGS outperforms existing methods on AGIQA benchmarks.

The use of task-specific prompts improves assessment accuracy.

Multi-granularity similarity enhances understanding of image quality details.

Abstract

Recently, AI-generated images (AIGIs) created by given prompts (initial prompts) have garnered widespread attention. Nevertheless, due to technical nonproficiency, they often suffer from poor perception quality and Text-to-Image misalignment. Therefore, assessing the perception quality and alignment quality of AIGIs is crucial to improving the generative model's performance. Existing assessment methods overly rely on the initial prompts in the task prompt design and use the same prompts to guide both perceptual and alignment quality evaluation, overlooking the distinctions between the two tasks. To address this limitation, we propose a novel quality assessment method for AIGIs named TSP-MGS, which designs task-specific prompts and measures multi-granularity similarity between AIGIs and the prompts. Specifically, task-specific prompts are first constructed to describe perception and alignment quality degrees separately, and the initial prompt is introduced for detailed quality perception. Then, the coarse-grained similarity between AIGIs and task-specific prompts is calculated, which facilitates holistic quality awareness. In addition, to improve the understanding of AIGI details, the fine-grained similarity between the image and the initial prompt is measured. Finally, precise quality prediction is acquired by integrating the multi-granularity similarities. Experiments on the commonly used AGIQA-1K and AGIQA-3K benchmarks demonstrate the superiority of the proposed TSP-MGS.