# JSRNN: Joint Sampling and Reconstruction Neural Networks for High Quality Image Compressed Sensing

arXiv: https://arxiv.org/abs/2211.05963 · HTML: https://mlsanity.com/paper/2211.05963/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 47 references that are in the map.
- First posted on arXiv 11 Nov 2022.

## Builds on (most cited first, 10 of 10)

- [From Denoising to Compressed Sensing](https://mlsanity.com/paper/1406.4175/) (2014)
- [AMP-Net: Denoising based Deep Unfolding for Compressive Image Sensing](https://mlsanity.com/paper/2004.10078/) (2020)
- [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)
- [Learning to Invert: Signal Recovery via Deep Convolutional Networks](https://mlsanity.com/paper/1701.03891/) (2017)
- [Abs-CAM: A Gradient Optimization Interpretable Approach for Explanation of Convolutional Neural Networks](https://mlsanity.com/paper/2207.03648/) (2022)
- [An ADMM-Based Interior-Point Method for Large-Scale Linear Programming](https://mlsanity.com/paper/1805.12344/) (2018)
- [A Deterministic and Generalized Framework for Unsupervised Learning with Restricted Boltzmann Machines](https://mlsanity.com/paper/1702.03260/) (2017)
- [Restricted Structural Random Matrix for Compressive Sensing](https://mlsanity.com/paper/2002.07346/) (2020)
- [A Robust Matching Pursuit Algorithm Using Information Theoretic Learning](https://mlsanity.com/paper/2005.04541/) (2020)

## Abstract (arXiv)

Most Deep Learning (DL) based Compressed Sensing (DCS) algorithms adopt a single neural network for signal reconstruction, and fail to jointly consider the influences of the sampling operation for reconstruction. In this paper, we propose unified framework, which jointly considers the sampling and reconstruction process for image compressive sensing based on well-designed cascade neural networks. Two sub-networks, which are the sampling sub-network and the reconstruction sub-network, are included in the proposed framework. In the sampling sub-network, an adaptive full connected layer instead of the traditional random matrix is used to mimic the sampling operator. In the reconstruction sub-network, a cascade network combining stacked denoising autoencoder (SDA) and convolutional neural network (CNN) is designed to reconstruct signals. The SDA is used to solve the signal mapping problem and the signals are initially reconstructed. Furthermore, CNN is used to fully recover the structure and texture features of the image to obtain better reconstruction performance. Extensive experiments show that this framework outperforms many other state-of-the-art methods, especially at low sampling rates.