[PDF]

Image Quality Assessment based on Large Language Models (LLMs)


Hao Zhang

25/08/2025

Supervised by Wei Zhou; Moderated by Usashi Chatterjee

While Large Language Models (LLMs) have experienced significant advancement in visual understanding, their potential to serve as powerful and text-driven models for Image Quality Assessment (IQA) remains largely unexplored. We would like to investigate the IQA task based on LLMs.


Final Report (25/08/2025) [Zip Archive]

Publication Form