ChangeAnywhere: Sample Generation for Remote Sensing Change Detection via Semantic Latent Diffusion Model

arXiv:2404.08892v1 Announce Type: cross
Abstract: Remote sensing change detection (CD) is a pivotal technique that pinpoints changes on a global scale based on multi-temporal images. With the recent expansion of deep learning, supervised deep learning-based CD models have shown satisfactory performance. However, CD sample labeling is very time-consuming as it is densely labeled and requires expert knowledge. To alleviate this problem, we introduce ChangeAnywhere, a novel CD sample generation method using the semantic latent diffusion model and single-temporal images. Specifically, …

arxiv change cs.ai cs.cv cs.lg detection diffusion diffusion model sample semantic sensing type via