SpecEStop: Self-Supervised Hyperspectral Mixed Noise Removal via Deep Spectral Prior.

Abstract

Hyperspectral remote sensing images often suffer from mixed noise-Gaussian, stripe, and impulse-due to atmospheric interference, solar variability, and sensor imperfections. These noises are typically band-dependent and diverse in distribution, making unified denoising particularly challenging. Existing deep denoising methods rely on clean/noisy pairs, which are unavailable in real-world remote sensing, while traditional approaches require manual tuning and lack adaptability. We propose SpecEStop, a fully self-supervised spectral vector denoising framework that requires only a single noisy HSI for training. Leveraging a novel deep spectral prior, SpecEStop exploits the spectral bias of neural networks, which tend to learn low-frequency (clean) signal components with Gaussian noise before overfitting to non-Gaussian noise ones. An adaptive early stopping strategy halts training before non-Gaussian noise is learned, enabling effective suppression of complex noise patterns. To address remaining Gaussian noise, we purposely design the network architecture to preserve its statistical properties in the latent space, allowing the use of off-the-shelf Gaussian denoisers during inference. Without any clean supervision, SpecEStop achieves effective, stage-wise removal of mixed noise, as validated across diverse real-world scenarios. Code will be released at https://github.com/ruobing-Zhang¹.