Compressive Light Field Reconstruction using Deep Learning
abstract: Light field imaging is limited in its computational processing demands of high sampling for both spatial and angular dimensions. Single-shot light field cameras sacrifice spatial resolution to sample angular viewpoints, typically by multiplexing incoming rays onto a 2D sensor array. Whi...
Other Authors: | |
---|---|
Format: | Dissertation |
Language: | English |
Published: |
2017
|
Subjects: | |
Online Access: | http://hdl.handle.net/2286/R.I.45525 |
id |
ndltd-asu.edu-item-45525 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-asu.edu-item-455252018-06-22T03:08:48Z Compressive Light Field Reconstruction using Deep Learning abstract: Light field imaging is limited in its computational processing demands of high sampling for both spatial and angular dimensions. Single-shot light field cameras sacrifice spatial resolution to sample angular viewpoints, typically by multiplexing incoming rays onto a 2D sensor array. While this resolution can be recovered using compressive sensing, these iterative solutions are slow in processing a light field. We present a deep learning approach using a new, two branch network architecture, consisting jointly of an autoencoder and a 4D CNN, to recover a high resolution 4D light field from a single coded 2D image. This network decreases reconstruction time significantly while achieving average PSNR values of 26-32 dB on a variety of light fields. In particular, reconstruction time is decreased from 35 minutes to 6.7 minutes as compared to the dictionary method for equivalent visual quality. These reconstructions are performed at small sampling/compression ratios as low as 8%, allowing for cheaper coded light field cameras. We test our network reconstructions on synthetic light fields, simulated coded measurements of real light fields captured from a Lytro Illum camera, and real coded images from a custom CMOS diffractive light field camera. The combination of compressive light field capture with deep learning allows the potential for real-time light field video acquisition systems in the future. Dissertation/Thesis Gupta, Mayank (Author) Turaga, Pavan (Advisor) Yang, Yezhou (Committee member) Li, Baoxin (Committee member) Arizona State University (Publisher) Computer engineering Electrical engineering compressive deep learning field light eng 46 pages Masters Thesis Computer Engineering 2017 Masters Thesis http://hdl.handle.net/2286/R.I.45525 http://rightsstatements.org/vocab/InC/1.0/ All Rights Reserved 2017 |
collection |
NDLTD |
language |
English |
format |
Dissertation |
sources |
NDLTD |
topic |
Computer engineering Electrical engineering compressive deep learning field light |
spellingShingle |
Computer engineering Electrical engineering compressive deep learning field light Compressive Light Field Reconstruction using Deep Learning |
description |
abstract: Light field imaging is limited in its computational processing demands of high
sampling for both spatial and angular dimensions. Single-shot light field cameras
sacrifice spatial resolution to sample angular viewpoints, typically by multiplexing
incoming rays onto a 2D sensor array. While this resolution can be recovered using
compressive sensing, these iterative solutions are slow in processing a light field. We
present a deep learning approach using a new, two branch network architecture,
consisting jointly of an autoencoder and a 4D CNN, to recover a high resolution
4D light field from a single coded 2D image. This network decreases reconstruction
time significantly while achieving average PSNR values of 26-32 dB on a variety of
light fields. In particular, reconstruction time is decreased from 35 minutes to 6.7
minutes as compared to the dictionary method for equivalent visual quality. These
reconstructions are performed at small sampling/compression ratios as low as 8%,
allowing for cheaper coded light field cameras. We test our network reconstructions
on synthetic light fields, simulated coded measurements of real light fields captured
from a Lytro Illum camera, and real coded images from a custom CMOS diffractive
light field camera. The combination of compressive light field capture with deep
learning allows the potential for real-time light field video acquisition systems in the
future. === Dissertation/Thesis === Masters Thesis Computer Engineering 2017 |
author2 |
Gupta, Mayank (Author) |
author_facet |
Gupta, Mayank (Author) |
title |
Compressive Light Field Reconstruction using Deep Learning |
title_short |
Compressive Light Field Reconstruction using Deep Learning |
title_full |
Compressive Light Field Reconstruction using Deep Learning |
title_fullStr |
Compressive Light Field Reconstruction using Deep Learning |
title_full_unstemmed |
Compressive Light Field Reconstruction using Deep Learning |
title_sort |
compressive light field reconstruction using deep learning |
publishDate |
2017 |
url |
http://hdl.handle.net/2286/R.I.45525 |
_version_ |
1718701565551837184 |