Image Compressed Sensing Using Non-local Neural Network

12/07/2021
by   Wenxue Cui, et al.
6

Deep network-based image Compressed Sensing (CS) has attracted much attention in recent years. However, the existing deep network-based CS schemes either reconstruct the target image in a block-by-block manner that leads to serious block artifacts or train the deep network as a black box that brings about limited insights of image prior knowledge. In this paper, a novel image CS framework using non-local neural network (NL-CSNet) is proposed, which utilizes the non-local self-similarity priors with deep network to improve the reconstruction quality. In the proposed NL-CSNet, two non-local subnetworks are constructed for utilizing the non-local self-similarity priors in the measurement domain and the multi-scale feature domain respectively. Specifically, in the subnetwork of measurement domain, the long-distance dependencies between the measurements of different image blocks are established for better initial reconstruction. Analogically, in the subnetwork of multi-scale feature domain, the affinities between the dense feature representations are explored in the multi-scale space for deep reconstruction. Furthermore, a novel loss function is developed to enhance the coupling between the non-local representations, which also enables an end-to-end training of NL-CSNet. Extensive experiments manifest that NL-CSNet outperforms existing state-of-the-art CS methods, while maintaining fast computational speed.

READ FULL TEXT

page 1

page 3

page 4

page 6

page 8

page 9

page 10

page 11

research
09/28/2022

Image Compressed Sensing with Multi-scale Dilated Convolutional Neural Network

Deep Learning (DL) based Compressed Sensing (CS) has been applied for be...
research
08/03/2022

Fast Hierarchical Deep Unfolding Network for Image Compressed Sensing

By integrating certain optimization solvers with deep neural network, de...
research
05/06/2023

NL-CS Net: Deep Learning with Non-Local Prior for Image Compressive Sensing

Deep learning has been applied to compressive sensing (CS) of images suc...
research
11/17/2019

Extra Proximal-Gradient Inspired Non-local Network

Variational method and deep learning method are two mainstream powerful ...
research
05/22/2023

Sparsity and Coefficient Permutation Based Two-Domain AMP for Image Block Compressed Sensing

The learned denoising-based approximate message passing (LDAMP) algorith...
research
07/03/2017

Deep Convolutional Framelets: A General Deep Learning Framework for Inverse Problems

Recently, deep learning approaches have achieved significant performance...
research
03/11/2019

Spatial-Aware Non-Local Attention for Fashion Landmark Detection

Fashion landmark detection is a challenging task even using the current ...

Please sign up or login with your details

Forgot password? Click here to reset