ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Sensing

TL;DR

ChangeBridge is a novel spatiotemporal image generation model for remote sensing that uses a drift-asynchronous diffusion bridge to generate coherent future scenes conditioned on pre-event images and multimodal controls.

Contribution

It introduces a new diffusion-based framework with three modules for modeling cross-temporal variations in remote sensing images, surpassing existing event-driven change methods.

Findings

Outperforms state-of-the-art methods in generating aligned spatiotemporal scenes.

Demonstrates potential for land-use planning and change detection tasks.

Shows high coherence in generated post-event scenes.

Abstract

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