Hyperspectral image reconstruction via patch attention driven network
Coded aperture snapshot spectral imaging (CASSI) captures 3D hyperspectral images (HSIs) with 2D compressive measurements. The recovery of HSIs from these measurements is an ill-posed problem. This paper proposes a novel, to our knowledge, network architecture for this inverse problem, which consists of a multilevel residual network driven by patch-wise attention and a data pre-processing method. Specifically, we propose the patch attention module to adaptively generate heuristic clues by capturing uneven feature distribution and global correlations of different regions. By revisiting the data pre-processing stage, we present a complementary input method that effectively integrates the measurements and coded aperture. Extensive simulation experiments illustrate that the proposed network architecture outperforms state-of-the-art methods.
This article was originally published in Optics Express. The version of record is available at: https://doi.org/10.1364/OE.479549. © 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement. Users may use, reuse, and build upon the article, or use the article for text or data mining, so long as such uses are for non-commercial purposes and appropriate attribution is maintained. All other rights are reserved.
Yechuan Qiu, Shengjie Zhao, Xu Ma, Tong Zhang, and Gonzalo R. Arce, "Hyperspectral image reconstruction via patch attention driven network," Opt. Express 31, 20221-20236 (2023)