Scalable Multi-Temporal Remote Sensing Change Data Generation via Simulating Stochastic Change Process

TL;DR

This paper introduces a scalable, generative approach for creating multi-temporal remote sensing change data using a probabilistic model, reducing the need for costly real data collection and annotation.

Contribution

It proposes a novel GAN-based probabilistic change model (GPCM) that simulates stochastic change processes for generating controllable multi-temporal remote sensing data.

Findings

Changen demonstrates superior generation quality.

Pre-trained change detectors transfer well to real datasets.

The method reduces data annotation costs.

Abstract

Understanding the temporal dynamics of Earth's surface is a mission of multi-temporal remote sensing image analysis, significantly promoted by deep vision models with its fuel -- labeled multi-temporal images. However, collecting, preprocessing, and annotating multi-temporal remote sensing images at scale is non-trivial since it is expensive and knowledge-intensive. In this paper, we present a scalable multi-temporal remote sensing change data generator via generative modeling, which is cheap and automatic, alleviating these problems. Our main idea is to simulate a stochastic change process over time. We consider the stochastic change process as a probabilistic semantic state transition, namely generative probabilistic change model (GPCM), which decouples the complex simulation problem into two more trackable sub-problems, \ie, change event simulation and semantic change synthesis. To solve these two problems, we present the change generator (Changen), a GAN-based GPCM, enabling controllable object change data generation, including customizable object property, and change event. The extensive experiments suggest that our Changen has superior generation capability, and the change detectors with Changen pre-training exhibit excellent transferability to real-world change datasets.