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

arXiv: https://arxiv.org/abs/2205.07770 · HTML: https://mlsanity.com/paper/2205.07770/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 60 references that are in the map.
- First posted on arXiv 16 May 2022.

## Builds on (most cited first, 18 of 18)

- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applications](https://mlsanity.com/paper/1605.01710/) (2016)
- [Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization](https://mlsanity.com/paper/1704.06327/) (2017)
- [Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging](https://mlsanity.com/paper/2003.13654/) (2020)
- [Medical image denoising using convolutional denoising autoencoders](https://mlsanity.com/paper/1608.04667/) (2016)
- [One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Models](https://mlsanity.com/paper/1703.09912/) (2017)
- [A Deep Learning Approach to Structured Signal Recovery](https://mlsanity.com/paper/1508.04065/) (2015)
- [DR2-Net: Deep Residual Reconstruction Network for Image Compressive Sensing](https://mlsanity.com/paper/1702.05743/) (2017)
- [NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image](https://mlsanity.com/paper/2005.03412/) (2020)
- [Learning to Invert: Signal Recovery via Deep Convolutional Networks](https://mlsanity.com/paper/1701.03891/) (2017)
- [Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification](https://mlsanity.com/paper/1606.06582/) (2016)
- [Deep Coded Aperture Design: An End-to-End Approach for Computational Imaging Tasks](https://mlsanity.com/paper/2105.03390/) (2021)
- [Compressive Spectral Image Reconstruction using Deep Prior and Low-Rank Tensor Representation](https://mlsanity.com/paper/2101.07424/) (2021)
- [Distributed Compressive Sensing: A Deep Learning Approach](https://mlsanity.com/paper/1508.04924/) (2015)
- [Proximal Alternating Direction Network: A Globally Converged Deep Unrolling Framework](https://mlsanity.com/paper/1711.07653/) (2017)
- [Solving Inverse Computational Imaging Problems using Deep Pixel-level Prior](https://mlsanity.com/paper/1802.09850/) (2018)
- [A Simple and Efficient Reconstruction Backbone for Snapshot Compressive Imaging](https://mlsanity.com/paper/2108.07739/) (2021)

## Built on by (most cited first, 5 of 5)

- [LD-GAN: Low-Dimensional Generative Adversarial Network for Spectral Image Generation with Variance Regularization](https://mlsanity.com/paper/2305.00132/) (2023)
- [Autoregressive High-Order Finite Difference Modulo Imaging: High-Dynamic Range for Computer Vision Applications](https://mlsanity.com/paper/2504.04228/) (2025)
- [D2UF: Deep Coded Aperture Design and Unrolling Algorithm for Compressive Spectral Image Fusion](https://mlsanity.com/paper/2205.12158/) (2022)
- [Mixture-Net: Low-Rank Deep Image Prior Inspired by Mixture Models for Spectral Image Recovery](https://mlsanity.com/paper/2211.02973/) (2022)
- [Deep Lightweight Unrolled Network for High Dynamic Range Modulo Imaging](https://mlsanity.com/paper/2601.12526/) (2026)

## 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.