RSICCLLM: A Multimodal Large Language Model for Remote Sensing Image Change Captioning

Remote Sensing Image Change Captioning holds significant research and application value because it aims to describe changes between bi-temporal remote sensing images yet existing methods are constrained by conventional deep learning architectures and limited model capacity.

Remote Sensing Image Change Captioning (RSICC) aims to describe changes between bi-temporal remote sensing images and holds significant research and application value. However, most existing methods rely on conventional deep learning architectures, and the limited model capacity…