Kolmogorov–Arnold Dynamic Gating Network With Dual-Domain Multiscale Feature Aggregation for Hyperspectral Stripe Noise Removal

Hyperspectral remote sensing satellites are an important tool in Earth observation technology, with hyperspectral images (HSIs) providing rich spectral information of the Earth's surface. However, due to various degradation factors in the imaging chain, HSIs are highly susceptible to stripe noise interference, which significantly degrades image quality. More troublingly, the stripe noise is easily mixed with the edges of the ground objects and background, making it difficult to effectively separate them. Additionally, existing methods have not sufficiently integrated frequency-domain and spectral information for stripe noise removal, leading to an inability to completely remove the noise. Moreover, the issue of preserving the original image structure and spectral information during the denoising process has been overlooked. In response to these challenges, this paper proposes the Kolmogorov-Arnold Dynamic Gating Network with Dual Domain Multi-Scale Feature Aggregation for Hyperspectral Stripe Noise Removal ($\rm{KAN-D}^{2}\rm{Net}$).$\rm{KAN-D}^{2}\rm{Net}$models stripe noise in the frequency domain to capture its anisotropic characteristics, integrates multi-scale spatial features to enhance expression capability, and uses a learnable graph structure to focus on key channels, improving spectral recovery. Additionally, it employs a KAN-based dynamic gating mechanism with a learnable activation function to adapt to complex data and boost nonlinear feature expression. Comparison with state-of-the-art methods shows that$\rm{KAN-D}^{2}\rm{Net}$effectively suppresses stripe noise and preserves original information, outperforming several existing techniques in both simulated and real hyperspectral data experiments.The code is available athttps://github.com/HAPPENnewbie/Kand2Net.git.