A High-Efficiency Diffusion Model-Inspired Network for Pixel-Level Self-Supervised Hyperspectral Anomaly Change Detection
Hyperspectral image change detection (CD) has garnered significant attention in the field of remote sensing. A critical task within CD is anomaly CD. Current generative anomaly CD methods, such as diffusion models, typically rely on computationally expensive iterative sampling to extract features, severely limiting their real-time application capabilities. Furthermore, in the absence of labeled data, existing unsupervised algorithms struggle to effectively distinguish subtle target variations from background artifacts caused by shadows or registration errors. To address these challenges, we propose a novel hyperspectral anomaly CD method named efficient latent denoising-inspired network (ELDI-Net). It employs a one-step manifold projection paradigm, achieving high computational efficiency while preserving the noise-robustness advantages of generative models. Specifically, we introduce a one-step latent manifold projection framework that transforms traditional iterative denoising into a deterministic latent mapping via an encoder–projector–decoder architecture, achieving a substantial improvement in inference speed. In addition, a spectral adaptive calibration projection module is constructed, employing channel-adaptive calibration to suppress spectral redundancy while effectively preserving critical features of subtle targets. A bidirectional focus alignment mechanism is designed for implicit semantic denoising under self-supervised conditions, suppressing pseudovariation artifacts through twin cross-prediction. Finally, a GCI strategy is introduced to eliminate directional sensor noise. Experimental results on three datasets demonstrate that the proposed ELDI-Net method achieves superior or highly competitive performance compared to multiple state-of-the-art approaches.