Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Super-Resolution in Compressive Coded Imaging Systems via l2 − l1 − l2 Minimization Under a Deep Learning Approach

Abstract: 

In most imaging applications the spatial resolution is a concern of the systems, but increasing the resolution of the sensor increases substantially the implementation cost. One option with lower cost is the use of spatial light modulators, which allows improving the reconstructed image resolution by including a high-resolution codification. In this paper, we propose a reconstruction methodology that exploits the intrinsic information contained in low-resolution measurements generated by the use of high-resolution spatial light modulators and high-resolution approximations obtained via a CNN. Specifically, based on a high-resolution CNN approximation, an l2 fidelity regularization term is introduced into a traditional l2 −l1 optimization problem. Finally, the simulations of the proposed l2 −l1 −l2 reconstruction approach show a quality improvement in up to 3.7dB in averaged PSNR against the use of the traditional l2 − l1 approach.

up
0 users have voted:

Paper Details

Authors:
Hans Garcia, Miguel Marquez, Henry Arguello
Submitted On:
31 March 2020 - 4:47am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Hans Garcia
Paper Code:
184
Session:
Session 2
Document Year:
2020
Cite

Document Files

Presentacion_DCC.pdf

(57)

Subscribe

[1] Hans Garcia, Miguel Marquez, Henry Arguello, "Super-Resolution in Compressive Coded Imaging Systems via l2 − l1 − l2 Minimization Under a Deep Learning Approach", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5075. Accessed: Aug. 13, 2020.
@article{5075-20,
url = {http://sigport.org/5075},
author = {Hans Garcia; Miguel Marquez; Henry Arguello },
publisher = {IEEE SigPort},
title = {Super-Resolution in Compressive Coded Imaging Systems via l2 − l1 − l2 Minimization Under a Deep Learning Approach},
year = {2020} }
TY - EJOUR
T1 - Super-Resolution in Compressive Coded Imaging Systems via l2 − l1 − l2 Minimization Under a Deep Learning Approach
AU - Hans Garcia; Miguel Marquez; Henry Arguello
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5075
ER -
Hans Garcia, Miguel Marquez, Henry Arguello. (2020). Super-Resolution in Compressive Coded Imaging Systems via l2 − l1 − l2 Minimization Under a Deep Learning Approach. IEEE SigPort. http://sigport.org/5075
Hans Garcia, Miguel Marquez, Henry Arguello, 2020. Super-Resolution in Compressive Coded Imaging Systems via l2 − l1 − l2 Minimization Under a Deep Learning Approach. Available at: http://sigport.org/5075.
Hans Garcia, Miguel Marquez, Henry Arguello. (2020). "Super-Resolution in Compressive Coded Imaging Systems via l2 − l1 − l2 Minimization Under a Deep Learning Approach." Web.
1. Hans Garcia, Miguel Marquez, Henry Arguello. Super-Resolution in Compressive Coded Imaging Systems via l2 − l1 − l2 Minimization Under a Deep Learning Approach [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5075