JR2net: A Joint Non-Linear Representation and Recovery Network for Compressive Spectral Imaging
This work addresses the efficiency and performance gap in compressive spectral imaging for applications like remote sensing or medical imaging, though it is incremental as it builds on existing deep learning approaches.
The paper tackled the problem of suboptimal representation in compressive spectral imaging recovery by proposing JR2net, a joint non-linear representation and recovery network, which achieved improvements up to 2.57 dB in PSNR and was around 2000 times faster than state-of-the-art methods.
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 network (CAE) 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 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 PSNR and performance around 2000 times faster than state-of-the-art methods.