Exploring Generalizable Pre-training for Real-world Change Detection via Geometric Estimation
This work addresses the complexity of change detection workflows in earth observation by reducing the need for prior manual registration, though it appears incremental as it builds on self-supervised and contrastive methods.
The paper tackles the problem of change detection in real-world scenarios where manual image registration is complex by proposing MatchCD, a self-supervised framework that simultaneously handles image unalignment and object changes, achieving promising performance on large-scale images up to 6K*4K resolution.
As an essential procedure in earth observation system, change detection (CD) aims to reveal the spatial-temporal evolution of the observation regions. A key prerequisite for existing change detection algorithms is aligned geo-references between multi-temporal images by fine-grained registration. However, in the majority of real-world scenarios, a prior manual registration is required between the original images, which significantly increases the complexity of the CD workflow. In this paper, we proposed a self-supervision motivated CD framework with geometric estimation, called "MatchCD". Specifically, the proposed MatchCD framework utilizes the zero-shot capability to optimize the encoder with self-supervised contrastive representation, which is reused in the downstream image registration and change detection to simultaneously handle the bi-temporal unalignment and object change issues. Moreover, unlike the conventional change detection requiring segmenting the full-frame image into small patches, our MatchCD framework can directly process the original large-scale image (e.g., 6K*4K resolutions) with promising performance. The performance in multiple complex scenarios with significant geometric distortion demonstrates the effectiveness of our proposed framework.