BTCChat: Advancing Remote Sensing Bi-temporal Change Captioning with Multimodal Large Language Model
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908789642362880 |
|---|---|
| author | Li, Yujie Xu, Wenjia Zhang, Yuanben Wei, Zhiwei Peng, Mugen |
| author_facet | Li, Yujie Xu, Wenjia Zhang, Yuanben Wei, Zhiwei Peng, Mugen |
| contents | Bi-temporal satellite imagery supports critical applications such as urbanization monitoring and disaster assessment. Although powerful multimodal large language models~(MLLMs) have been applied in bi-temporal change analysis, previous methods process image pairs through direct concatenation, inadequately modeling temporal correlations and spatial semantic changes. This deficiency hampers visual-semantic alignment in change understanding, thereby constraining the overall effectiveness of current approaches. To address this gap, we propose BTCChat, a multi-temporal MLLM with advanced bi-temporal change understanding capability. BTCChat supports bi-temporal change captioning and retains single-image interpretation capability. To better capture temporal features and spatial semantic changes in image pairs, we design a Change Extraction module. Moreover, to enhance the model's attention to spatial details, we introduce a Prompt Augmentation mechanism, which incorporates contextual clues into the prompt to enhance model performance. Experimental results demonstrate that BTCChat achieves state-of-the-art performance on change captioning and visual question answering tasks. The code is available \href{https://github.com/IntelliSensing/BTCChat}{here}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_05895 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BTCChat: Advancing Remote Sensing Bi-temporal Change Captioning with Multimodal Large Language Model Li, Yujie Xu, Wenjia Zhang, Yuanben Wei, Zhiwei Peng, Mugen Computer Vision and Pattern Recognition Bi-temporal satellite imagery supports critical applications such as urbanization monitoring and disaster assessment. Although powerful multimodal large language models~(MLLMs) have been applied in bi-temporal change analysis, previous methods process image pairs through direct concatenation, inadequately modeling temporal correlations and spatial semantic changes. This deficiency hampers visual-semantic alignment in change understanding, thereby constraining the overall effectiveness of current approaches. To address this gap, we propose BTCChat, a multi-temporal MLLM with advanced bi-temporal change understanding capability. BTCChat supports bi-temporal change captioning and retains single-image interpretation capability. To better capture temporal features and spatial semantic changes in image pairs, we design a Change Extraction module. Moreover, to enhance the model's attention to spatial details, we introduce a Prompt Augmentation mechanism, which incorporates contextual clues into the prompt to enhance model performance. Experimental results demonstrate that BTCChat achieves state-of-the-art performance on change captioning and visual question answering tasks. The code is available \href{https://github.com/IntelliSensing/BTCChat}{here}. |
| title | BTCChat: Advancing Remote Sensing Bi-temporal Change Captioning with Multimodal Large Language Model |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.05895 |