Quality Assessment for AI Generated Images With Instruction Tuning

作者：Jiarui Wang, Huiyu Duan, Guangtao Zhai, Xiongkuo Min · 发表于：IEEE Transactions on Multimedia · 年份：2026 · DOI：10.1109/tmm.2026.3651009 · 被引用次数：7 · 研究领域：Visual Attention and Saliency Detection、Multimodal Machine Learning Applications、Generative Adversarial Networks and Image Synthesis

Artificial Intelligence Generated Content (AIGC) has grown rapidly in recent years, among which AI-based image generation has gained widespread attention due to its efficient and imaginative image creation ability. However, AI-generated Images (AIGIs) may not satisfy human preferences due to their unique distortions, which highlights the necessity to understand and evaluate human preferences for AIGIs. To this end, in this paper, we first establish a novel Image Quality Assessment (IQA) database for AIGIs, termed AIGCIQA2023+, which provides human visual preference scores and detailed preference explanations from three perspectives including quality, authenticity, and correspondence. Then, based on the constructed AIGCIQA2023+ database, this paper presents aMINT-IQAmodel to evaluate and explain human preferences for AIGIs fromMulti-perspectives withINstructionTuning. Specifically, the MINT-IQA model first learn and evaluate human preferences for AI-generated Images from multi-perspectives, then via the vision-language instruction tuning strategy, MINT-IQA attains powerful understanding and explanation ability for human visual preference on AIGIs, which can be used for feedback to further improve the assessment capabilities. Extensive experimental results demonstrate that the proposed MINT-IQA model achieves state-of-the-art performance in understanding and evaluating human visual preferences for AIGIs, and the proposed model also achieves competing results on traditional IQA ...