Large Multi-modality Model Assisted AI-Generated Image Quality Assessment

TL;DR

This paper introduces MA-AGIQA, a multi-modality model that enhances AI-generated image quality assessment by incorporating semantic understanding through text prompts and a mixture of experts, outperforming existing models.

Contribution

The paper proposes a novel multi-modality approach with semantic guidance and a mixture of experts to improve AGI quality assessment, addressing limitations of traditional DNN-based models.

Findings

Achieves state-of-the-art performance on AIGCQA-20k and AGIQA-3k datasets.

Demonstrates superior generalization in assessing AI-generated images.

Effectively integrates semantic information with quality features.

Abstract

Traditional deep neural network (DNN)-based image quality assessment (IQA) models leverage convolutional neural networks (CNN) or Transformer to learn the quality-aware feature representation, achieving commendable performance on natural scene images. However, when applied to AI-Generated images (AGIs), these DNN-based IQA models exhibit subpar performance. This situation is largely due to the semantic inaccuracies inherent in certain AGIs caused by uncontrollable nature of the generation process. Thus, the capability to discern semantic content becomes crucial for assessing the quality of AGIs. Traditional DNN-based IQA models, constrained by limited parameter complexity and training data, struggle to capture complex fine-grained semantic features, making it challenging to grasp the existence and coherence of semantic content of the entire image. To address the shortfall in semantic content perception of current IQA models, we introduce a large Multi-modality model Assisted AI-Generated Image Quality Assessment (MA-AGIQA) model, which utilizes semantically informed guidance to sense semantic information and extract semantic vectors through carefully designed text prompts. Moreover, it employs a mixture of experts (MoE) structure to dynamically integrate the semantic information with the quality-aware features extracted by traditional DNN-based IQA models. Comprehensive experiments conducted on two AI-generated content datasets, AIGCQA-20k and AGIQA-3k show that MA-AGIQA achieves state-of-the-art performance, and demonstrate its superior generalization capabilities on assessing the quality of AGIs. Code is available at https://github.com/wangpuyi/MA-AGIQA.