{"ID":2888618,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.22346","arxiv_id":"2507.22346","title":"DeltaVLM: Interactive Remote Sensing Image Change Analysis via Instruction-guided Difference Perception","abstract":"Accurate interpretation of land-cover changes in multi-temporal satellite imagery is critical for real-world scenarios. However, existing methods typically provide only one-shot change masks or static captions, limiting their ability to support interactive, query-driven analysis. In this work, we introduce remote sensing image change analysis (RSICA) as a new paradigm that combines the strengths of change detection and visual question answering to enable multi-turn, instruction-guided exploration of changes in bi-temporal remote sensing images. To support this task, we construct ChangeChat-105k, a large-scale instruction-following dataset, generated through a hybrid rule-based and GPT-assisted process, covering six interaction types: change captioning, classification, quantification, localization, open-ended question answering, and multi-turn dialogues. Building on this dataset, we propose DeltaVLM, an end-to-end architecture tailored for interactive RSICA. DeltaVLM features three innovations: (1) a fine-tuned bi-temporal vision encoder to capture temporal differences; (2) a visual difference perception module with a cross-semantic relation measuring (CSRM) mechanism to interpret changes; and (3) an instruction-guided Q-former to effectively extract query-relevant difference information from visual changes, aligning them with textual instructions. We train DeltaVLM on ChangeChat-105k using a frozen large language model, adapting only the vision and alignment modules to optimize efficiency. Extensive experiments and ablation studies demonstrate that DeltaVLM achieves state-of-the-art performance on both single-turn captioning and multi-turn interactive change analysis, outperforming existing multimodal large language models and remote sensing vision-language models. Code, dataset and pre-trained weights are available at https://github.com/hanlinwu/DeltaVLM.","short_abstract":"Accurate interpretation of land-cover changes in multi-temporal satellite imagery is critical for real-world scenarios. However, existing methods typically provide only one-shot change masks or static captions, limiting their ability to support interactive, query-driven analysis. In this work, we introduce remote sensi...","url_abs":"https://arxiv.org/abs/2507.22346","url_pdf":"https://arxiv.org/pdf/2507.22346v1","authors":"[\"Pei Deng\",\"Wenqian Zhou\",\"Hanlin Wu\"]","published":"2025-07-30T03:14:27Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\",\"LoRA\"]","has_code":false,"code_links":[{"ID":611558,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2888618,"paper_url":"https://arxiv.org/abs/2507.22346","paper_title":"DeltaVLM: Interactive Remote Sensing Image Change Analysis via Instruction-guided Difference Perception","repo_url":"https://github.com/hanlinwu/DeltaVLM","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}