Morphing Through Time: Diffusion-Based Bridging of Temporal Gaps for Robust Alignment in Change Detection

The introduction of a modular pipeline for remote sensing change detection represents a significant advancement in addressing the persistent challenge of spatial misalignment between bi-temporal images, particularly when there are long gaps between acquisitions. Traditional models often struggle under these conditions due to their reliance on precise co-registration. The new framework integrates diffusion-based semantic morphing, dense registration, and residual flow refinement, allowing it to enhance spatial and temporal robustness without altering existing change detection networks. Extensive experiments conducted on datasets such as LEVIR-CD, WHU-CD, and DSIFN-CD have shown consistent gains in both registration accuracy and overall change detection performance. This development not only demonstrates the generality and effectiveness of the proposed approach but also sets a new standard for future research in the field, potentially leading to more reliable applications in environmenta…