TitleCREAM: CNN-REgularized ADMM Framework for Compressive-Sensed Image Reconstruction
AuthorsZhao, Chen
Zhang, Jian
Wang, Ronggang
Gao, Wen
AffiliationPeking Univ, Sch Elect & Comp Engn, Shenzhen Grad Sch, Shenzhen 518055, Peoples R China.
Peking Univ, Sch Elect Engn & Comp Sci, Beijing 100871, Peoples R China.
KeywordsCompressive sensing
deep learning
alternate direction method of multipliers (ADMM)
convolutional neural network (CNN)
image reconstruction
THRESHOLDING ALGORITHM
Issue Date2018
PublisherIEEE ACCESS
CitationIEEE ACCESS. 2018, 6, 76838-76853.
AbstractCompressive sensing (CS) has drawn an enormous amount of attention in recent years due to its sub-Nyquist sampling rate and low-complexity requirement at the encoder. However, it turns out that the decoder in lieu of the encoder suffers from heavy computation in order to decently recover the signal from its CS measurements. With the aim of developing a fast yet accurate algorithm, in this paper, we propose to leverage a deep convolutional neural network (CNN) prior model to the constrained CS reconstruction formulation and solve it via the alternating direction method of multipliers (ADMM). The proposed CNN-REgularized ADMM framework, dubbed CREAM, is able to recover image signals from CS measurements effectively and efficiently. On the one hand, the developed constrained CS formulation by CREAM enables fewer regularization parameters and less computational complexity compared with traditional unconstrained CS formulation by ADMM. On the other hand, rather than training a neural network from scratch, an off-the-shelf CNN model is directly incorporated into CREAM even without the effort of fine tuning, in which CNN has exhibited its desirable reconstruction performance and low computational complexity. Hereby, powerful GPU can be utilized to speed up the reconstruction. Experiments demonstrate that our proposed method for CS reconstruction of natural images surpasses state-of-the-art CS models by a significant margin in speed and performance.
URIhttp://hdl.handle.net/20.500.11897/572370
ISSN2169-3536
DOI10.1109/ACCESS.2018.2882990
IndexedSCI(E)
Appears in Collections:信息工程学院
信息科学技术学院

Files in This Work
There are no files associated with this item.

Web of Science®



Checked on Last Week

Scopus®



Checked on Current Time

百度学术™



Checked on Current Time

Google Scholar™





License: See PKU IR operational policies.