Toward Multi-Dimensional Quality Assessment of AI-Generated Images via Prompt-Guided Relational Learning
- 17 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Broadcasting
- Vol. PP (00189316) , 1-13
Abstract
The explosive growth of Artificial Intelligence Generated Images (AGIs) has created an urgent need for automated quality assessment. Unlike traditional image quality assessment, AGIs evaluation faces core challenges such as the absence of reference images, the need to integrate textual information, and the multi-dimensional nature of evaluation criteria. Existing methods typically rely on shared multimodal features for unified modeling, failing to effectively address two key issues: the differentiated extraction of dimension-specific features and the modeling of intrinsic relationships between dimensions. To address this, this paper proposes a Prompt-guided Relationship Learning Network (PRL-Net). Specifically, we first design a dimension-specific prompt attention (DPA) module, which introduces learnable prompts for each quality dimension to guide the model in adaptively focusing on dimension-related feature representations from shared features. Furthermore, we introduce a cross-dimensional graph relational attention (CGRA) module that explicitly models the complex dependencies between different quality dimensions (such as quality, consistency, and authenticity) through a dynamic graph neural network, enabling cross-dimensional feature interaction and information complementarity. Experimental results on multiple public benchmark datasets demonstrate that PRL-Net outperforms existing state-of-the-art methods across several evaluation metrics, validating its effectiveness.Keywords
Funding Information
- National Natural Science Foundation of China (62471263)
- Science and Technology Innovation Yongjiang 2035 Key Technology Breakthrough Plan Project in Ningbo (2024Z113)
- National Natural Science Foundation of China
This publication has 49 references indexed in Scilit:
- Cross-Modality Interactive Attention Network for AI-generated image quality assessmentPattern Recognition, 2025
- CLIP-AGIQA: Boosting the Performance of AI-Generated Image Quality Assessment with CLIP2024
- AIGC Image Quality Assessment via Image-Prompt Correspondence2024
- MoE-AGIQA: Mixture-of-Experts Boosted Visual Perception-Driven and Semantic-Aware Quality Assessment for AI-Generated Images2024
- AIGCIQA2023: A Large-Scale Image Quality Assessment Database for AI Generated Images: From the Perspectives of Quality, Authenticity and Correspondence2024
- Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective2023
- MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment2022
- Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network2020
- Deep Residual Learning for Image Recognition2016
- Convolutional Neural Networks for No-Reference Image Quality Assessment2014