ChangeBridge：面向遥感的多模态控制时空图像生成
ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Senisng
扩散桥（diffusion bridge）用给定前事件图像作为起点替代噪声初始化，并用像素级漂移图区分事件变化与时序变化，这一「从观测状态出发、按漂移量差异化生成」的框架可直接迁移到视频预测、时序遥感与变化检测的数据增广。
原文依据 The core idea is a drift-asynchronous diffusion bridge.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论时空图像生成是一项极具意义的任务，能够以给定观测为条件生成未来场景。然而，现有的变化生成方法只能处理事件驱动型变化（例如新增建筑），无法建模跨时序变化（例如季节更替）。本文提出 ChangeBridge，一种面向遥感的条件时空图像生成模型。给定前事件图像与多模态事件控制，ChangeBridge 生成在空间与时序上均连贯的后事件场景。其核心思想是漂移异步扩散桥。具体而言，它由三个主要模块构成：a）组合桥初始化，用于替代噪声初始化，从组合的前事件状态出发启动扩散过程，从而建模扩散桥过程；b）异步漂移扩散，使用逐像素漂移图，为事件演化与时序演化分配不同的漂移幅度，从而在前到后的过渡中实现差异化生成；c）漂移感知去噪，将漂移图嵌入去噪网络，引导漂移感知的重建。实验表明，与最优方法相比，ChangeBridge 能够生成跨时空对齐更优的场景。此外，ChangeBridge 在土地利用规划以及作为一系列变化检测任务的数据生成引擎方面展现出巨大潜力。代码见 https://github.com/zhenghuizhao/ChangeBridge。
英文原文摘要 1496 字符
Spatiotemporal image generation is a highly meaningful task, which can generate future scenes conditioned on given observations. However, existing change generation methods can only handle event-driven changes (e.g., new buildings) and fail to model cross-temporal variations (e.g., seasonal shifts). In this work, we propose ChangeBridge, a conditional spatiotemporal image generation model for remote sensing. Given pre-event images and multimodal event controls, ChangeBridge generates post-event scenes that are both spatially and temporally coherent. The core idea is a drift-asynchronous diffusion bridge. Specifically, it consists of three main modules: a) Composed Bridge Initialization, which replaces noise initialization. It starts the diffusion from a composed pre-event state, modeling a diffusion bridge process. b) Asynchronous Drift Diffusion, which uses a pixel-wise drift map, assigning different drift magnitudes to event and temporal evolution. This enables differentiated generation during the pre-to-post transition. c) Drift-Aware Denoising, which embeds the drift map into the denoising network, guiding drift-aware reconstruction. Experiments show that ChangeBridge can generate better cross-spatiotemporal aligned scenarios compared to state-of-the-art methods. Additionally, ChangeBridge shows great potential for land-use planning and as a data generation engine for a series of change detection tasks. Code is available at https://github.com/zhenghuizhao/ChangeBridge