國立虎尾科技大學 |

Combining Learning and Computational Imaging for 3D Inference.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Combining Learning and Computational Imaging for 3D Inference./
Author:	Guo, Xinqing.
Description:	1 online resource (122 pages)
Notes:	Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.
Subject:	Computer science. -
Online resource:	click for full text (PQDT)
ISBN:	9780355734782

Combining Learning and Computational Imaging for 3D Inference.
Guo, Xinqing.

Combining Learning and Computational Imaging for 3D Inference. - 1 online resource (122 pages)

Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.

Thesis (Ph.D.)--University of Delaware, 2017.

Includes bibliographical references

Acquiring 3D geometry of the scene is a key task in computer vision. Applications are numerous, from classical object reconstruction and scene understanding to the more recent visual SLAM and autonomous driving. Recent advances in computational imaging have enabled many new solutions to tackle the problem of 3D reconstruction. By modifying the camera's components, computational imaging optically encodes the scene, then decodes it with tailored algorithms.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355734782Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Combining Learning and Computational Imaging for 3D Inference.
LDR:03794ntm a2200361K 4500 001 912181
005 20180608102941.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355734782
035 $a (MiAaPQ)AAI10642051
035 $a (MiAaPQ)udel:13132
035 $a AAI10642051
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Guo, Xinqing. $3 1184424
245 1 0 $a Combining Learning and Computational Imaging for 3D Inference.
264 0 $c 2017
300 $a 1 online resource (122 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.
500 $a Adviser: Jingyi Yu.
502 $a Thesis (Ph.D.)--University of Delaware, 2017.
504 $a Includes bibliographical references
520 $a Acquiring 3D geometry of the scene is a key task in computer vision. Applications are numerous, from classical object reconstruction and scene understanding to the more recent visual SLAM and autonomous driving. Recent advances in computational imaging have enabled many new solutions to tackle the problem of 3D reconstruction. By modifying the camera's components, computational imaging optically encodes the scene, then decodes it with tailored algorithms.
520 $a This dissertation focuses on exploring new computational imaging techniques, combined with recent advances in deep learning, to infer 3D geometry of the scene. In general, our approaches can be categorized into active and passive 3D sensing.
520 $a For active illumination methods, we propose two solutions: first, we present a multi-flash (MF) system implemented on the mobile platform. Using the sequence of images captured by the MF system, we can extract the depth edges of the scene, and further estimate a depth map on a mobile device. Next, we show a portable immersive system that is capable of acquiring and displaying high fidelity 3D reconstructions using a set of RGB-D sensors. The system is based on structured light technique and is able to recover 3D geometry of the scene in real time. We have also developed a visualization system that allows users to dynamically visualize the event from new perspectives at arbitrary time instances in real time.
520 $a For passive sensing methods, we focus on light field based depth estimation. For depth inference from a single light field, we present an algorithm that is tailored for barcode images. Our algorithm analyzes the statistics of raw light field images and conducts depth estimation with real time speed for fast refocusing and decoding. To mimic the human vision system, we investigate the dual light field input and propose a unified deep learning based framework to extract depth from both disparity cue and focus cue. To facilitate training, we have created a large dual focal stack database with ground truth disparity. While above solution focuses on fusing depth from focus and stereo, we also exploit combing depth from defocus and stereo, with an all-focus stereo pair and a defocused image of one of the stereo views as input. We have adopted the hourglass network architecture to extract depth from the image triplets. We have then studied and explored multiple neural network architectures to improve depth inference. We demonstrate that our deep learning based approaches preserve the strength of focus/defocus cue and disparity cue while effectively suppressing their weaknesses.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Artificial intelligence. $3 559380
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Delaware. $b Computer and Information Sciences. $3 1183446
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10642051 $z click for full text (PQDT)