Saved in:
Bibliographic Details
Main Authors: Zhao, Zhenghui, Wu, Chen, Cao, Xiangyong, Wang, Di, Chen, Hongruixuan, Tang, Datao, Zhang, Liangpei, Zheng, Zhuo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.04678
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913017185173504
author Zhao, Zhenghui
Wu, Chen
Cao, Xiangyong
Wang, Di
Chen, Hongruixuan
Tang, Datao
Zhang, Liangpei
Zheng, Zhuo
author_facet Zhao, Zhenghui
Wu, Chen
Cao, Xiangyong
Wang, Di
Chen, Hongruixuan
Tang, Datao
Zhang, Liangpei
Zheng, Zhuo
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2507_04678
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Sensing
Zhao, Zhenghui
Wu, Chen
Cao, Xiangyong
Wang, Di
Chen, Hongruixuan
Tang, Datao
Zhang, Liangpei
Zheng, Zhuo
Computer Vision and Pattern Recognition
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
title ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Sensing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.04678