Optimizing Mask and Dictionary of Compressive Light Field Photography

Zhangyu Yao, Yunhui Shi, Wenpeng Ding, Baocai Yin, Junbin Gao

Research output: Book chapter/Published conference paperConference paper

Abstract

A compressive light field camera architecture has been proposed to recover light fields from a single image. This technique has recently gained increasing interest. The reconstruction quality of light field depends on the incoherence of a projection matrix and dictionary. Compressive light field acquisition is different from acquiring traditional signal while the projection matrix has specific structural features. In this paper, we propose a new design for the mask to compute the optimized projection and a new method to optimize the dictionary for compressive light field. The contribution of this paper comprises of twofold: designing the mask to compute the optimized projection matrix from a known dictionary of compressive light field, and training the optimized dictionary when the projection is fixed. Experimental results show that our method can improve the reconstruction quality of light field views comparing with the random projection mask.
Original languageEnglish
Title of host publicationICDH 2014
Place of PublicationUnited States
PublisherIEEE
Pages168-172
Number of pages5
ISBN (Electronic)9781479942848
DOIs
Publication statusPublished - 2014
EventInternational Conference on Digital Home - Guangzhou, China, China
Duration: 28 Nov 201430 Nov 2014

Conference

ConferenceInternational Conference on Digital Home
CountryChina
Period28/11/1430/11/14

Fingerprint

dictionaries
photography
masks
projection
matrices
incoherence
acquisition
education
cameras

Cite this

Yao, Z., Shi, Y., Ding, W., Yin, B., & Gao, J. (2014). Optimizing Mask and Dictionary of Compressive Light Field Photography. In ICDH 2014 (pp. 168-172). United States: IEEE. https://doi.org/10.1109/ICDH.2014.40
Yao, Zhangyu ; Shi, Yunhui ; Ding, Wenpeng ; Yin, Baocai ; Gao, Junbin. / Optimizing Mask and Dictionary of Compressive Light Field Photography. ICDH 2014. United States : IEEE, 2014. pp. 168-172
@inproceedings{5775b9cc744740618e6064a4f7c7ee20,
title = "Optimizing Mask and Dictionary of Compressive Light Field Photography",
abstract = "A compressive light field camera architecture has been proposed to recover light fields from a single image. This technique has recently gained increasing interest. The reconstruction quality of light field depends on the incoherence of a projection matrix and dictionary. Compressive light field acquisition is different from acquiring traditional signal while the projection matrix has specific structural features. In this paper, we propose a new design for the mask to compute the optimized projection and a new method to optimize the dictionary for compressive light field. The contribution of this paper comprises of twofold: designing the mask to compute the optimized projection matrix from a known dictionary of compressive light field, and training the optimized dictionary when the projection is fixed. Experimental results show that our method can improve the reconstruction quality of light field views comparing with the random projection mask.",
keywords = "compressive sensing; dictionary learning; light field; optimized projection",
author = "Zhangyu Yao and Yunhui Shi and Wenpeng Ding and Baocai Yin and Junbin Gao",
note = "Imported on 03 May 2017 - DigiTool details were: publisher = IEEE, 2014. Event dates (773o) = 28-11-2014-30-11-2014; Parent title (773t) = International Conference on Digital Home.",
year = "2014",
doi = "10.1109/ICDH.2014.40",
language = "English",
pages = "168--172",
booktitle = "ICDH 2014",
publisher = "IEEE",

}

Yao, Z, Shi, Y, Ding, W, Yin, B & Gao, J 2014, Optimizing Mask and Dictionary of Compressive Light Field Photography. in ICDH 2014. IEEE, United States, pp. 168-172, International Conference on Digital Home, China, 28/11/14. https://doi.org/10.1109/ICDH.2014.40

Optimizing Mask and Dictionary of Compressive Light Field Photography. / Yao, Zhangyu; Shi, Yunhui; Ding, Wenpeng; Yin, Baocai; Gao, Junbin.

ICDH 2014. United States : IEEE, 2014. p. 168-172.

Research output: Book chapter/Published conference paperConference paper

TY - GEN

T1 - Optimizing Mask and Dictionary of Compressive Light Field Photography

AU - Yao, Zhangyu

AU - Shi, Yunhui

AU - Ding, Wenpeng

AU - Yin, Baocai

AU - Gao, Junbin

N1 - Imported on 03 May 2017 - DigiTool details were: publisher = IEEE, 2014. Event dates (773o) = 28-11-2014-30-11-2014; Parent title (773t) = International Conference on Digital Home.

PY - 2014

Y1 - 2014

N2 - A compressive light field camera architecture has been proposed to recover light fields from a single image. This technique has recently gained increasing interest. The reconstruction quality of light field depends on the incoherence of a projection matrix and dictionary. Compressive light field acquisition is different from acquiring traditional signal while the projection matrix has specific structural features. In this paper, we propose a new design for the mask to compute the optimized projection and a new method to optimize the dictionary for compressive light field. The contribution of this paper comprises of twofold: designing the mask to compute the optimized projection matrix from a known dictionary of compressive light field, and training the optimized dictionary when the projection is fixed. Experimental results show that our method can improve the reconstruction quality of light field views comparing with the random projection mask.

AB - A compressive light field camera architecture has been proposed to recover light fields from a single image. This technique has recently gained increasing interest. The reconstruction quality of light field depends on the incoherence of a projection matrix and dictionary. Compressive light field acquisition is different from acquiring traditional signal while the projection matrix has specific structural features. In this paper, we propose a new design for the mask to compute the optimized projection and a new method to optimize the dictionary for compressive light field. The contribution of this paper comprises of twofold: designing the mask to compute the optimized projection matrix from a known dictionary of compressive light field, and training the optimized dictionary when the projection is fixed. Experimental results show that our method can improve the reconstruction quality of light field views comparing with the random projection mask.

KW - compressive sensing; dictionary learning; light field; optimized projection

U2 - 10.1109/ICDH.2014.40

DO - 10.1109/ICDH.2014.40

M3 - Conference paper

SP - 168

EP - 172

BT - ICDH 2014

PB - IEEE

CY - United States

ER -

Yao Z, Shi Y, Ding W, Yin B, Gao J. Optimizing Mask and Dictionary of Compressive Light Field Photography. In ICDH 2014. United States: IEEE. 2014. p. 168-172 https://doi.org/10.1109/ICDH.2014.40