mlsanityData to 7 Oct 2026

JR2net: A Joint Non-Linear Representation and Recovery Network for Compressive Spectral Imaging

arXiv 2205.07770 ↗First posted 16 May 2022eess.IV cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 18 of its 60 references that are in the map. First posted on arXiv 16 May 2022.

Builds on

18 of 60 references.

References · 18

  1. 2021Convex optimizationcited by 2,479
  2. 2017Deep Image Priorcited by 1,097
  3. 2016Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applicationscited by 244
  4. 2017Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimizationcited by 113
  5. 2020Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imagingcited by 78
  6. 2016Medical image denoising using convolutional denoising autoencoderscited by 76
  7. 2017One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Modelscited by 67
  8. 2015A Deep Learning Approach to Structured Signal Recoverycited by 43
  9. 2017DR2-Net: Deep Residual Reconstruction Network for Image Compressive Sensingcited by 30
  10. 2020NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Imagecited by 30
  11. 2017Learning to Invert: Signal Recovery via Deep Convolutional Networkscited by 22
  12. 2016Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classificationcited by 18
6 more
  1. 2021Deep Coded Aperture Design: An End-to-End Approach for Computational Imaging Taskscited by 12
  2. 2021Compressive Spectral Image Reconstruction using Deep Prior and Low-Rank Tensor Representationcited by 7
  3. 2015Distributed Compressive Sensing: A Deep Learning Approachcited by 6
  4. 2017Proximal Alternating Direction Network: A Globally Converged Deep Unrolling Frameworkcited by 2
  5. 2018Solving Inverse Computational Imaging Problems using Deep Pixel-level Priorcited by 2
  6. 2021A Simple and Efficient Reconstruction Backbone for Snapshot Compressive Imagingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 1; 2024: 0; 2025: 1; 2026: 1.

5 papers.

  1. 2023LD-GAN: Low-Dimensional Generative Adversarial Network for Spectral Image Generation with Variance Regularizationcited by 2
  2. 2022D2UF: Deep Coded Aperture Design and Unrolling Algorithm for Compressive Spectral Image Fusioncited by 1
  3. 2022Mixture-Net: Low-Rank Deep Image Prior Inspired by Mixture Models for Spectral Image Recoverycited by 1
  4. 2025Autoregressive High-Order Finite Difference Modulo Imaging: High-Dynamic Range for Computer Vision Applicationscited by 1
  5. 2026Deep Lightweight Unrolled Network for High Dynamic Range Modulo Imagingcited by 0