Log In Sign Up

Multi-Scale Deep Compressive Sensing Network

by   Thuong Nguyen Canh, et al.

With joint learning of sampling and recovery, the deep learning-based compressive sensing (DCS) has shown significant improvement in performance and running time reduction. Its reconstructed image, however, losses high-frequency content especially at low subrates. This happens similarly in the multi-scale sampling scheme which also samples more low-frequency components. In this paper, we propose a multi-scale DCS convolutional neural network (MS-DCSNet) in which we convert image signal using multiple scale-based wavelet transform, then capture it through convolution block by block across scales. The initial reconstructed image is directly recovered from multi-scale measurements. Multi-scale wavelet convolution is utilized to enhance the final reconstruction quality. The network is able to learn both multi-scale sampling and multi-scale reconstruction, thus results in better reconstruction quality.


Multi-Scale Deep Compressive Imaging

Recently, deep learning-based compressive imaging (DCI) has surpassed th...

Image Compressed Sensing with Multi-scale Dilated Convolutional Neural Network

Deep Learning (DL) based Compressed Sensing (CS) has been applied for be...

Subspace Decomposition based DNN algorithm for elliptic-type multi-scale PDEs

While deep learning algorithms demonstrate a great potential in scientif...

Random Convolution Kernels with Multi-Scale Decomposition for Preterm EEG Inter-burst Detection

Linear classifiers with random convolution kernels are computationally e...

Wavelet Transform-assisted Adaptive Generative Modeling for Colorization

Unsupervised deep learning has recently demonstrated the promise to prod...

Multi-scale classification for electro-sensing

This paper introduces premier and innovative (real-time) multi-scale met...