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

facebooktwittermailshare

GENERATIVE MODELS FOR LOW-RANK VIDEO REPRESENTATION AND RECONSTRUCTION FROM COMPRESSIVE MEASUREMENTS

Abstract: 

Generative models have recently received considerable attention in the field of compressive sensing. If an image belongs to the range of a pretrained generative network, we can recover it from its compressive measurements by estimating the underlying compact latent code. In practice, all the pretrained generators have certain range beyond which they fail to generate reliably. Recent researches show that convolutional generative structures are biased to generate natural images. Based on this hypothesis, we propose joint optimization of latent codes and the weights of the generative network in compressive sensing. The main advantage of this method is that we no longer need a pretrained generator as we are optimizing weights of the network. Furthermore, we are getting compact representation of each image from latent code optimization. We empirically demonstrate that our proposed method provides better or comparable accuracy and low complexity compared to the existing methods on different video compressive sensing problems.

For details: https://arxiv.org/pdf/1902.11132.pdf (18)

up
0 users have voted:

Paper Details

Authors:
M. Salman Asif
Submitted On:
4 December 2019 - 7:13am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Rakib Hyder
Paper Code:
214
Document Year:
2019
Cite

Document Files

Poster_GENERATIVE MODELS_Hyder

(32)

Subscribe

[1] M. Salman Asif, "GENERATIVE MODELS FOR LOW-RANK VIDEO REPRESENTATION AND RECONSTRUCTION FROM COMPRESSIVE MEASUREMENTS", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4966. Accessed: Feb. 26, 2020.
@article{4966-19,
url = {http://sigport.org/4966},
author = {M. Salman Asif },
publisher = {IEEE SigPort},
title = {GENERATIVE MODELS FOR LOW-RANK VIDEO REPRESENTATION AND RECONSTRUCTION FROM COMPRESSIVE MEASUREMENTS},
year = {2019} }
TY - EJOUR
T1 - GENERATIVE MODELS FOR LOW-RANK VIDEO REPRESENTATION AND RECONSTRUCTION FROM COMPRESSIVE MEASUREMENTS
AU - M. Salman Asif
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4966
ER -
M. Salman Asif. (2019). GENERATIVE MODELS FOR LOW-RANK VIDEO REPRESENTATION AND RECONSTRUCTION FROM COMPRESSIVE MEASUREMENTS. IEEE SigPort. http://sigport.org/4966
M. Salman Asif, 2019. GENERATIVE MODELS FOR LOW-RANK VIDEO REPRESENTATION AND RECONSTRUCTION FROM COMPRESSIVE MEASUREMENTS. Available at: http://sigport.org/4966.
M. Salman Asif. (2019). "GENERATIVE MODELS FOR LOW-RANK VIDEO REPRESENTATION AND RECONSTRUCTION FROM COMPRESSIVE MEASUREMENTS." Web.
1. M. Salman Asif. GENERATIVE MODELS FOR LOW-RANK VIDEO REPRESENTATION AND RECONSTRUCTION FROM COMPRESSIVE MEASUREMENTS [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4966