Decoding the Delta: Unifying Remote Sensing Change Detection and Understanding with Multimodal Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911596001886208 |
|---|---|
| author | Li, Xiaohe Li, Jiahao Zhang, Kaixin Fang, Yuqiang Lin, Leilei Wang, Hong Wu, Haohua Fan, Zide |
| author_facet | Li, Xiaohe Li, Jiahao Zhang, Kaixin Fang, Yuqiang Lin, Leilei Wang, Hong Wu, Haohua Fan, Zide |
| contents | While Multimodal Large Language Models (MLLMs) excel in general vision-language tasks, their application to remote sensing change understanding is hindered by a fundamental "temporal blindness". Existing architectures lack intrinsic mechanisms for multi-temporal contrastive reasoning and struggle with precise spatial grounding. To address this, we first introduce Delta-QA, a comprehensive benchmark comprising 180k visual question-answering samples. Delta-QA unifies pixel-level segmentation and visual question answering across bi- and tri-temporal scenarios, structuring change interpretation into four progressive cognitive dimensions. Methodologically, we propose Delta-LLaVA, a novel MLLM framework explicitly tailored for multi-temporal remote sensing interpretation. It overcomes the limitations of naive feature concatenation through three core innovations: a Change-Enhanced Attention module that systematically isolates and amplifies visual differences, a Change-SEG module utilizing Change Prior Embedding to extract differentiable difference features as input for the LLM, and Local Causal Attention to prevent cross-temporal contextual leakage. Extensive experiments demonstrate that Delta-LLaVA decisively outperforms leading generalist MLLMs and specialized segmentation models in complex change deduction and high-precision boundary localization, establishing a unified framework for earth observation intelligence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_14044 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Decoding the Delta: Unifying Remote Sensing Change Detection and Understanding with Multimodal Large Language Models Li, Xiaohe Li, Jiahao Zhang, Kaixin Fang, Yuqiang Lin, Leilei Wang, Hong Wu, Haohua Fan, Zide Computer Vision and Pattern Recognition While Multimodal Large Language Models (MLLMs) excel in general vision-language tasks, their application to remote sensing change understanding is hindered by a fundamental "temporal blindness". Existing architectures lack intrinsic mechanisms for multi-temporal contrastive reasoning and struggle with precise spatial grounding. To address this, we first introduce Delta-QA, a comprehensive benchmark comprising 180k visual question-answering samples. Delta-QA unifies pixel-level segmentation and visual question answering across bi- and tri-temporal scenarios, structuring change interpretation into four progressive cognitive dimensions. Methodologically, we propose Delta-LLaVA, a novel MLLM framework explicitly tailored for multi-temporal remote sensing interpretation. It overcomes the limitations of naive feature concatenation through three core innovations: a Change-Enhanced Attention module that systematically isolates and amplifies visual differences, a Change-SEG module utilizing Change Prior Embedding to extract differentiable difference features as input for the LLM, and Local Causal Attention to prevent cross-temporal contextual leakage. Extensive experiments demonstrate that Delta-LLaVA decisively outperforms leading generalist MLLMs and specialized segmentation models in complex change deduction and high-precision boundary localization, establishing a unified framework for earth observation intelligence. |
| title | Decoding the Delta: Unifying Remote Sensing Change Detection and Understanding with Multimodal Large Language Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.14044 |