Reconnet

Non-iterative reconstruction of images from compressively sensed measurements

Kuldeep Kulkarni, Suhas Lohit, Pavan Turaga, Ronan Kerviche, Amit Ashok

Research output: Chapter in Book/Report/Conference proceedingConference contribution

96 Citations (Scopus)

Abstract

The goal of this paper is to present a non-iterative and more importantly an extremely fast algorithm to reconstruct images from compressively sensed (CS) random measurements. To this end, we propose a novel convolutional neural network (CNN) architecture which takes in CS measurements of an image as input and outputs an intermediate reconstruction. We call this network, ReconNet. The intermediate reconstruction is fed into an off-the-shelf denoiser to obtain the final reconstructed image. On a standard dataset of images we show significant improvements in reconstruction results (both in terms of PSNR and time complexity) over state-of-the-art iterative CS reconstruction algorithms at various measurement rates. Further, through qualitative experiments on real data collected using our block single pixel camera (SPC), we show that our network is highly robust to sensor noise and can recover visually better quality images than competitive algorithms at extremely low sensing rates of 0.1 and 0.04. To demonstrate that our algorithm can recover semantically informative images even at a low measurement rate of 0.01, we present a very robust proof of concept real-time visual tracking application.

Original languageEnglish (US)
Title of host publication2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
PublisherIEEE Computer Society
Pages449-458
Number of pages10
Volume2016-January
ISBN (Electronic)9781467388511
StatePublished - 2016
Event2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 - Las Vegas, United States
Duration: Jun 26 2016Jul 1 2016

Other

Other2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
CountryUnited States
CityLas Vegas
Period6/26/167/1/16

Fingerprint

Network architecture
Image quality
Pixels
Cameras
Neural networks
Sensors
Experiments

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Kulkarni, K., Lohit, S., Turaga, P., Kerviche, R., & Ashok, A. (2016). Reconnet: Non-iterative reconstruction of images from compressively sensed measurements. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 (Vol. 2016-January, pp. 449-458). IEEE Computer Society.

Reconnet : Non-iterative reconstruction of images from compressively sensed measurements. / Kulkarni, Kuldeep; Lohit, Suhas; Turaga, Pavan; Kerviche, Ronan; Ashok, Amit.

2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. Vol. 2016-January IEEE Computer Society, 2016. p. 449-458.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kulkarni, K, Lohit, S, Turaga, P, Kerviche, R & Ashok, A 2016, Reconnet: Non-iterative reconstruction of images from compressively sensed measurements. in 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. vol. 2016-January, IEEE Computer Society, pp. 449-458, 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, United States, 6/26/16.
Kulkarni K, Lohit S, Turaga P, Kerviche R, Ashok A. Reconnet: Non-iterative reconstruction of images from compressively sensed measurements. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. Vol. 2016-January. IEEE Computer Society. 2016. p. 449-458
Kulkarni, Kuldeep ; Lohit, Suhas ; Turaga, Pavan ; Kerviche, Ronan ; Ashok, Amit. / Reconnet : Non-iterative reconstruction of images from compressively sensed measurements. 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. Vol. 2016-January IEEE Computer Society, 2016. pp. 449-458
@inproceedings{9fcd1ed5040f4eca948ce7139d34140e,
title = "Reconnet: Non-iterative reconstruction of images from compressively sensed measurements",
abstract = "The goal of this paper is to present a non-iterative and more importantly an extremely fast algorithm to reconstruct images from compressively sensed (CS) random measurements. To this end, we propose a novel convolutional neural network (CNN) architecture which takes in CS measurements of an image as input and outputs an intermediate reconstruction. We call this network, ReconNet. The intermediate reconstruction is fed into an off-the-shelf denoiser to obtain the final reconstructed image. On a standard dataset of images we show significant improvements in reconstruction results (both in terms of PSNR and time complexity) over state-of-the-art iterative CS reconstruction algorithms at various measurement rates. Further, through qualitative experiments on real data collected using our block single pixel camera (SPC), we show that our network is highly robust to sensor noise and can recover visually better quality images than competitive algorithms at extremely low sensing rates of 0.1 and 0.04. To demonstrate that our algorithm can recover semantically informative images even at a low measurement rate of 0.01, we present a very robust proof of concept real-time visual tracking application.",
author = "Kuldeep Kulkarni and Suhas Lohit and Pavan Turaga and Ronan Kerviche and Amit Ashok",
year = "2016",
language = "English (US)",
volume = "2016-January",
pages = "449--458",
booktitle = "2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016",
publisher = "IEEE Computer Society",
address = "United States",

}

TY - GEN

T1 - Reconnet

T2 - Non-iterative reconstruction of images from compressively sensed measurements

AU - Kulkarni, Kuldeep

AU - Lohit, Suhas

AU - Turaga, Pavan

AU - Kerviche, Ronan

AU - Ashok, Amit

PY - 2016

Y1 - 2016

N2 - The goal of this paper is to present a non-iterative and more importantly an extremely fast algorithm to reconstruct images from compressively sensed (CS) random measurements. To this end, we propose a novel convolutional neural network (CNN) architecture which takes in CS measurements of an image as input and outputs an intermediate reconstruction. We call this network, ReconNet. The intermediate reconstruction is fed into an off-the-shelf denoiser to obtain the final reconstructed image. On a standard dataset of images we show significant improvements in reconstruction results (both in terms of PSNR and time complexity) over state-of-the-art iterative CS reconstruction algorithms at various measurement rates. Further, through qualitative experiments on real data collected using our block single pixel camera (SPC), we show that our network is highly robust to sensor noise and can recover visually better quality images than competitive algorithms at extremely low sensing rates of 0.1 and 0.04. To demonstrate that our algorithm can recover semantically informative images even at a low measurement rate of 0.01, we present a very robust proof of concept real-time visual tracking application.

AB - The goal of this paper is to present a non-iterative and more importantly an extremely fast algorithm to reconstruct images from compressively sensed (CS) random measurements. To this end, we propose a novel convolutional neural network (CNN) architecture which takes in CS measurements of an image as input and outputs an intermediate reconstruction. We call this network, ReconNet. The intermediate reconstruction is fed into an off-the-shelf denoiser to obtain the final reconstructed image. On a standard dataset of images we show significant improvements in reconstruction results (both in terms of PSNR and time complexity) over state-of-the-art iterative CS reconstruction algorithms at various measurement rates. Further, through qualitative experiments on real data collected using our block single pixel camera (SPC), we show that our network is highly robust to sensor noise and can recover visually better quality images than competitive algorithms at extremely low sensing rates of 0.1 and 0.04. To demonstrate that our algorithm can recover semantically informative images even at a low measurement rate of 0.01, we present a very robust proof of concept real-time visual tracking application.

UR - http://www.scopus.com/inward/record.url?scp=84986249771&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84986249771&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2016-January

SP - 449

EP - 458

BT - 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

PB - IEEE Computer Society

ER -