Abstract
Hyperspectral image denoising is unique for the highly similar and correlated spectral information that should be properly considered. However, existing methods show limitations in exploring the spectral correlations across different bands and feature interactions within each band. Besides, the low- and high-level features usually exhibit different importance for different spatial-spectral regions, which is not fully explored for current algorithms as well. In this paper, we present a Mixed Attention Network (MAN) that simultaneously considers the inter- and intra-spectral correlations as well as the interactions between low- and high-level spatial-spectral meaningful features. Specifically, we introduce a multi-head recurrent spectral attention that efficiently integrates the inter-spectral features across all the spectral bands. These features are further enhanced with a progressive spectral channel attention by exploring the intra-spectral relationships. Moreover, we propose an attentive skip-connection that adaptively controls the proportion of the low- and high-level spatial-spectral features from the encoder and decoder to better enhance the aggregated features. Extensive experiments show that our MAN outperforms existing state-of-the-art methods on simulated and real noise settings while maintaining a low cost of parameters and running time.
Abstract (translated)
超分辨率图像去噪对于那些高度相似且相关的光谱信息来说是非常独特的,这些信息应该得到充分的考虑。然而,现有的方法在探索不同 Band 之间的光谱 correlation 以及每个 Band 内部的特征相互作用方面显示出局限性。此外,低和高级别特征通常在不同的空间-光谱区域中表现出不同的重要性,当前算法也没有完全探索这种情况。在本文中,我们提出了一种混合注意力网络(MAN),可以同时考虑Inter-和Intra-spectral correlation 以及低和高级别空间-光谱 meaningful features之间的相互作用。具体来说,我们引入了多个头循环的超分辨率注意力,高效地整合了所有 Band 之间的跨 Band 超分辨率特征。通过探索内积超分辨率关系,这些特征还可以通过渐进的超分辨率通道注意力进一步增强。此外,我们提出了一种注意跳过连接,自适应地控制编码器和解码器中低和高级别空间-光谱特征的比例,以更好地增强聚合特征。广泛的实验结果表明,我们的 Man 在模拟和真实噪声设置中比现有的先进方法表现更好,同时参数和运行成本都很低。
URL
https://arxiv.org/abs/2301.11525
