Real-Time Reconstruction of 3D Compressive Samples with Deep Learning

Vladislav Kravets; Adrian Stern

doi:10.1364/3D.2022.3F2A.2

Real-Time Reconstruction of 3D Compressive Samples with Deep Learning

Vladislav Kravets, Adrian Stern

School of Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We present a real-time 3D compressive samples reconstruction by using a deep learning network for variable density Hadamard samples. Our method is able to successfully recover 3D examples from as few as 10 samples.

Original language	English
Title of host publication	3D Image Acquisition and Display
Subtitle of host publication	Technology, Perception and Applications, 3D 2022
Publisher	Optica Publishing Group (formerly OSA)
ISBN (Electronic)	9781957171098
DOIs	https://doi.org/10.1364/3D.2022.3F2A.2
State	Published - 1 Jan 2022
Event	3D Image Acquisition and Display: Technology, Perception and Applications, 3D 2022 - Vancouver, Canada Duration: 11 Jul 2022 → 15 Jul 2022

Publication series

Name	Optics InfoBase Conference Papers
ISSN (Electronic)	2162-2701

Conference

Conference	3D Image Acquisition and Display: Technology, Perception and Applications, 3D 2022
Country/Territory	Canada
City	Vancouver
Period	11/07/22 → 15/07/22

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Mechanics of Materials

Access to Document

10.1364/3D.2022.3F2A.2

Cite this

@inproceedings{4c615eb2a9594c6b9ed72483ec57a852,

title = "Real-Time Reconstruction of 3D Compressive Samples with Deep Learning",

abstract = "We present a real-time 3D compressive samples reconstruction by using a deep learning network for variable density Hadamard samples. Our method is able to successfully recover 3D examples from as few as 10 samples.",

author = "Vladislav Kravets and Adrian Stern",

note = "Publisher Copyright: {\textcopyright} 2022 The Author(s); 3D Image Acquisition and Display: Technology, Perception and Applications, 3D 2022 ; Conference date: 11-07-2022 Through 15-07-2022",

year = "2022",

month = jan,

day = "1",

doi = "10.1364/3D.2022.3F2A.2",

language = "English",

series = "Optics InfoBase Conference Papers",

publisher = "Optica Publishing Group (formerly OSA)",

booktitle = "3D Image Acquisition and Display",

}

Kravets, V & Stern, A 2022, Real-Time Reconstruction of 3D Compressive Samples with Deep Learning. in 3D Image Acquisition and Display: Technology, Perception and Applications, 3D 2022., 3F2A.2, Optics InfoBase Conference Papers, Optica Publishing Group (formerly OSA), 3D Image Acquisition and Display: Technology, Perception and Applications, 3D 2022, Vancouver, Canada, 11/07/22. https://doi.org/10.1364/3D.2022.3F2A.2

Real-Time Reconstruction of 3D Compressive Samples with Deep Learning. / Kravets, Vladislav; Stern, Adrian.
3D Image Acquisition and Display: Technology, Perception and Applications, 3D 2022. Optica Publishing Group (formerly OSA), 2022. 3F2A.2 (Optics InfoBase Conference Papers).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Real-Time Reconstruction of 3D Compressive Samples with Deep Learning

AU - Kravets, Vladislav

AU - Stern, Adrian

PY - 2022/1/1

Y1 - 2022/1/1

N2 - We present a real-time 3D compressive samples reconstruction by using a deep learning network for variable density Hadamard samples. Our method is able to successfully recover 3D examples from as few as 10 samples.

AB - We present a real-time 3D compressive samples reconstruction by using a deep learning network for variable density Hadamard samples. Our method is able to successfully recover 3D examples from as few as 10 samples.

UR - http://www.scopus.com/inward/record.url?scp=85139115284&partnerID=8YFLogxK

U2 - 10.1364/3D.2022.3F2A.2

DO - 10.1364/3D.2022.3F2A.2

M3 - Conference contribution

AN - SCOPUS:85139115284

T3 - Optics InfoBase Conference Papers

BT - 3D Image Acquisition and Display

PB - Optica Publishing Group (formerly OSA)

T2 - 3D Image Acquisition and Display: Technology, Perception and Applications, 3D 2022

Y2 - 11 July 2022 through 15 July 2022

ER -

Real-Time Reconstruction of 3D Compressive Samples with Deep Learning

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this