用隐空间流模型生成连贯变化区域，提升遥感图像变化检测精度。
ChangeFlow -- Latent Rectified Flow for Change Detection in Remote Sensing
- 在紧凑隐空间中通过修正流生成变化掩码，避免碎片化预测。
- 四个二值基准上平均F1达80.4%，比之前最佳高1.3点，且更高效。
- 适用于语义变化检测，新设基准SECOND上达65.9的F_scd，适合遥感分析者。
遥感变化检测（RSCD）旨在定位同一地理区域两幅图像间的差异。现有主流方法采用逐像素判别式目标，独立分类每个位置，导致预测结果常呈零散分布。生成建模提供了一种系统性解决方案：通过学习合理变化掩码的分布，将掩码视为整体对象，促进全局一致性。然而，现有生成式方法因像素空间生成成本高、条件机制复杂，性能仍落后于强判别基线。本文提出 extbf{ChangeFlow}，将变化检测重构为在紧凑隐空间中通过修正流生成变化掩码，并以结构化但轻量的双时相条件信号引导。该方法实现空间连贯预测且不牺牲效率：在四个二值基准SYSU、LEVIR、CLCD和OSCD上，平均F1达$80.4\\$，较前人最优提升$1.3$点；同时扩展至语义变化检测，在SECOND数据集上取得$65.9$的$F_{scd}$新纪录。
原文摘要 · Abstract (English)
Remote sensing change detection (RSCD) localises changes between two images of the same geographic region. Most state-of-the-art methods are trained with a per-pixel discriminative objective that classifies each spatial location independently. In this scenario, the predicted changed region is not modelled as a coherent whole, so predictions tend to be spatially fragmented. Generative modelling offers a principled solution: by learning a distribution over plausible change masks, it treats the mask as a single object and encourages global consistency. Yet existing generative RSCD methods lag behind strong discriminative baselines, held back by costly pixel-space generation and overly complex conditioning. We introduce \textbf{ChangeFlow}, which reformulates change detection as the generative synthesis of change masks in a compact latent space via rectified flow, guided by a structured yet lightweight bi-temporal conditioning signal. Changeflow yields spatially coherent predictions without sacrificing efficiency: across four binary benchmarks, SYSU, LEVIR, CLCD, and OSCD, ChangeFlow achieves an average F1 of $80.4\%$, a $1.3$-point gain over the previous best with better efficiency. It also extends to semantic change detection, setting a new state-of-the-art $65.9$ $F_{scd}$ on SECOND. Project page: https://blaz-r.github.io/changeflow_cd
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。