TIER: Text-Image Encoder-based Regression for AIGC Image Quality Assessment

TL;DR

This paper introduces TIER, a novel framework that leverages text prompts and generated images using encoders to improve AI-generated image quality assessment, outperforming existing methods.

Contribution

The paper proposes a text-image encoder-based regression framework that incorporates text prompts into quality assessment, addressing limitations of previous image-only approaches.

Findings

TIER outperforms baseline methods on multiple AIGCIQA datasets.

Incorporating text prompts improves the accuracy of image quality prediction.

Extensive experiments validate the effectiveness of the proposed approach.

Abstract

Recently, AIGC image quality assessment (AIGCIQA), which aims to assess the quality of AI-generated images (AIGIs) from a human perception perspective, has emerged as a new topic in computer vision. Unlike common image quality assessment tasks where images are derived from original ones distorted by noise, blur, and compression, \textit{etc.}, in AIGCIQA tasks, images are typically generated by generative models using text prompts. Considerable efforts have been made in the past years to advance AIGCIQA. However, most existing AIGCIQA methods regress predicted scores directly from individual generated images, overlooking the information contained in the text prompts of these images. This oversight partially limits the performance of these AIGCIQA methods. To address this issue, we propose a text-image encoder-based regression (TIER) framework. Specifically, we process the generated images and their corresponding text prompts as inputs, utilizing a text encoder and an image encoder to extract features from these text prompts and generated images, respectively. To demonstrate the effectiveness of our proposed TIER method, we conduct extensive experiments on several mainstream AIGCIQA databases, including AGIQA-1K, AGIQA-3K, and AIGCIQA2023. The experimental results indicate that our proposed TIER method generally demonstrates superior performance compared to baseline in most cases.