IEEE

Teaching Large Language Models to Regress Accurate Image Quality Scores Using Score Distribution

Abstract: With the rapid advancement of Multi-modal Large Language Models (MLLMs), MLLM-based Image Quality Assessment (IQA) methods have shown promising performance in linguistic quality description.
IEEE

Fine-tuned Multimodal Large Language Models are Zero-shot Learners in Image Quality Assessment

Abstract: Image quality assessment (IQA) has traditionally relied on task-specific models, often limiting their adaptability and generalization to diverse image content. To this end, this paper ...