Abstract
Deep learning models are state-of-the-art in compressive spectral imaging (CSI) recovery. These methods use a deep neural network (DNN) as an image generator to learn non-linear mapping from compressed measurements to the spectral image. For instance, the deep spectral prior approach uses a convolutional autoencoder (CAE) network in the optimization algorithm to recover the spectral image by using a non-linear representation. However, the CAE training is detached from the recovery problem, which does not guarantee optimal representation of the spectral images for the CSI problem. This work proposes a joint non-linear representation and recovery network (JR2net), linking the representation and recovery task into a single optimization problem. JR2net consists of an optimization-inspired network following an alternating direction method of multipliers (ADMM) formulation that learns a non-linear low-dimensional representation and simultaneously performs the spectral image recovery, trained via the end-to-end approach. Experimental results show the superiority of the proposed method with improvements up to 2.57 dB in peak signal-to-noise ratio (PSNR) and performance around 2000 times faster than state-of-the-art methods.
© 2022 Optica Publishing Group
Full Article | PDF ArticleMore Like This
Jorge Bacca, Yesid Fonseca, and Henry Arguello
Appl. Opt. 60(14) 4197-4207 (2021)
Juan F. Florez-Ospina, Abdullah K. M. Alrushud, Daniel L. Lau, and Gonzalo R. Arce
Opt. Express 30(5) 7187-7209 (2022)
Zhenming Yu, Diyi Liu, Liming Cheng, Ziyi Meng, Zhengxiang Zhao, Xin Yuan, and Kun Xu
Opt. Express 30(26) 46822-46837 (2022)