Remote sensing change detection plays a pivotal role in domains such as environmental monitoring, urban planning, and disaster assessment. However, existing methods typically rely on predefined categories and large-scale pixel-level annotations, which limit their generalization and applicability in open-world scenarios. To address these limitations, this paper proposes AdaptOVCD, a training-free Open-Vocabulary Change Detection (OVCD) architecture based on dual-dimensional multi-level information fusion. The framework integrates multi-level information fusion across data, feature, and decision levels vertically while incorporating targeted adaptive designs horizontally, achieving deep synergy among heterogeneous pre-trained models to effectively mitigate error propagation. Specifically, (1) at the data level, Adaptive Radiometric Alignment (ARA) fuses radiometric statistics with original texture features and synergizes with SAM-HQ to achieve radiometrically consistent segmentation; (2) at the feature level, Adaptive Change Thresholding (ACT) combines global difference distributions with edge structure priors and leverages DINOv3 to achieve robust change detection; (3) at the decision level, Adaptive Confidence Filtering (ACF) integrates semantic confidence with spatial constraints and collaborates with DGTRS-CLIP to achieve high-confidence semantic identification. Comprehensive evaluations across nine scenarios demonstrate that AdaptOVCD detects arbitrary category changes in a zero-shot manner, significantly outperforming existing training-free methods. Meanwhile, it achieves 84.89\% of the fully-supervised performance upper bound in cross-dataset evaluations and exhibits superior generalization capabilities. The code is available at https://github.com/Dmygithub/AdaptOVCD.

翻译：遥感变化检测在环境监测、城市规划与灾害评估等领域发挥着关键作用。然而，现有方法通常依赖于预定义类别和大规模像素级标注，这限制了其在开放世界场景中的泛化能力和适用性。为克服这些局限，本文提出AdaptOVCD，一种基于双维多级信息融合的免训练开放词汇变化检测架构。该框架在纵向上融合数据、特征与决策三个层次的多级信息，在横向上引入针对性的自适应设计，实现异构预训练模型间的深度协同，有效抑制误差传播。具体而言：（1）在数据层面，自适应辐射对齐融合辐射统计量与原始纹理特征，并与SAM-HQ协同实现辐射一致的分割；（2）在特征层面，自适应变化阈值化结合全局差异分布与边缘结构先验，并利用DINOv3实现鲁棒的变化检测；（3）在决策层面，自适应置信度过滤集成语义置信度与空间约束，并协同DGTRS-CLIP实现高置信度的语义识别。在九种场景下的综合评估表明，AdaptOVCD能够以零样本方式检测任意类别变化，显著优于现有免训练方法。同时，其在跨数据集评估中达到全监督性能上限的84.89%，展现出优异的泛化能力。代码公开于https://github.com/Dmygithub/AdaptOVCD。