Region-Aware Sequence-to-Sequence Learning for Hyperspectral Denoising

Abstract

Proper spectral modeling within hyperspectral image (HSI) is critical yet highly challenging for HSI denoising. In contrast to existing methods that struggle between effectiveness and flexibility in modeling long-range spectral dependencies and directly explore spatial-spectral information without region discrimination, we introduce RAS2S—a simple yet effective sequence-to-sequence (Seq2Seq) learning framework for better HSI denoising. RAS2S treats HSI denoising as a Seq2Seq translation problem, which converts the noisy spectral sequence to its clean ones in an autoregressive fashion. In addition, spatial-spectral information exploration without region discrimination contradicts the intrinsic spatial-spectral diversity of HSIs, leading to negative interference from spatial-spectral unrelated regions. Thus we propose a novel spatial-spectral region-aware module to distinctively perceive the semantic regions with different spatial-spectral representations, maximizing the spectral modeling potential of Seq2Seq learning. With such an improved Seq2Seq learning paradigm, RAS2S not only shows huge potential in capturing long-range spectral dependencies, but also maintains the flexibility to handle diverse HSIs. Extensive experiments demonstrate that RAS2S outperforms existing state-of-the-art methods quantitatively and qualitatively with a minimal model size, merely 0.08M. Source code is available at https: //github.com/MIV-XJTU/RAS2S.