Generative adversarial network based image blur compensation for projection-based mixed reality

Yuta Kageyama; Mariko Isogawa; Daisuke Iwai; Kosuke Sato

doi:10.1109/GCCE46687.2019.9015415

Generative adversarial network based image blur compensation for projection-based mixed reality

Yuta Kageyama, Mariko Isogawa, Daisuke Iwai, Kosuke Sato

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

1 Citation (Scopus)

Abstract

Projection-based mixed reality superimposes an image on a real object by a projector. There is a problem that spatially nonuniform blurring occurs in the projected result due to defocus blur and subsurface scattering. As the solution, some methods of applying blur compensation to an input image before projecting have been studied. In this paper, we propose to use a generative adversarial network (GAN) that computes the compensation image from an input image and a projected result.

Original language	English
Title of host publication	2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	227-228
Number of pages	2
ISBN (Electronic)	9781728135755
DOIs	https://doi.org/10.1109/GCCE46687.2019.9015415
Publication status	Published - 2019 Oct
Externally published	Yes
Event	8th IEEE Global Conference on Consumer Electronics, GCCE 2019 - Osaka, Japan Duration: 2019 Oct 15 → 2019 Oct 18

Publication series

Name	2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019

Conference

Conference	8th IEEE Global Conference on Consumer Electronics, GCCE 2019
Country/Territory	Japan
City	Osaka
Period	19/10/15 → 19/10/18

Keywords

Blur compensation
Convolutional neural network (CNN)
Generative adversarial network (GAN)
Projection-based mixed reality

ASJC Scopus subject areas

Instrumentation
Artificial Intelligence
Computer Networks and Communications
Computer Science Applications
Electrical and Electronic Engineering

Access to Document

10.1109/GCCE46687.2019.9015415

Cite this

Kageyama, Y., Isogawa, M., Iwai, D., & Sato, K. (2019). Generative adversarial network based image blur compensation for projection-based mixed reality. In 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019 (pp. 227-228). [9015415] (2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GCCE46687.2019.9015415

Generative adversarial network based image blur compensation for projection-based mixed reality. / Kageyama, Yuta; Isogawa, Mariko; Iwai, Daisuke et al.

2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 227-228 9015415 (2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019).

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

Kageyama, Y, Isogawa, M, Iwai, D & Sato, K 2019, Generative adversarial network based image blur compensation for projection-based mixed reality. in 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019., 9015415, 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019, Institute of Electrical and Electronics Engineers Inc., pp. 227-228, 8th IEEE Global Conference on Consumer Electronics, GCCE 2019, Osaka, Japan, 19/10/15. https://doi.org/10.1109/GCCE46687.2019.9015415

Kageyama Y, Isogawa M, Iwai D, Sato K. Generative adversarial network based image blur compensation for projection-based mixed reality. In 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 227-228. 9015415. (2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019). doi: 10.1109/GCCE46687.2019.9015415

@inproceedings{674f33302c4f4b97861a4c190c5acdb6,

title = "Generative adversarial network based image blur compensation for projection-based mixed reality",

abstract = "Projection-based mixed reality superimposes an image on a real object by a projector. There is a problem that spatially nonuniform blurring occurs in the projected result due to defocus blur and subsurface scattering. As the solution, some methods of applying blur compensation to an input image before projecting have been studied. In this paper, we propose to use a generative adversarial network (GAN) that computes the compensation image from an input image and a projected result.",

keywords = "Blur compensation, Convolutional neural network (CNN), Generative adversarial network (GAN), Projection-based mixed reality",

author = "Yuta Kageyama and Mariko Isogawa and Daisuke Iwai and Kosuke Sato",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 8th IEEE Global Conference on Consumer Electronics, GCCE 2019 ; Conference date: 15-10-2019 Through 18-10-2019",

year = "2019",

month = oct,

doi = "10.1109/GCCE46687.2019.9015415",

language = "English",

series = "2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "227--228",

booktitle = "2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019",

}

TY - GEN

T1 - Generative adversarial network based image blur compensation for projection-based mixed reality

AU - Kageyama, Yuta

AU - Isogawa, Mariko

AU - Iwai, Daisuke

AU - Sato, Kosuke

PY - 2019/10

Y1 - 2019/10

N2 - Projection-based mixed reality superimposes an image on a real object by a projector. There is a problem that spatially nonuniform blurring occurs in the projected result due to defocus blur and subsurface scattering. As the solution, some methods of applying blur compensation to an input image before projecting have been studied. In this paper, we propose to use a generative adversarial network (GAN) that computes the compensation image from an input image and a projected result.

AB - Projection-based mixed reality superimposes an image on a real object by a projector. There is a problem that spatially nonuniform blurring occurs in the projected result due to defocus blur and subsurface scattering. As the solution, some methods of applying blur compensation to an input image before projecting have been studied. In this paper, we propose to use a generative adversarial network (GAN) that computes the compensation image from an input image and a projected result.

KW - Blur compensation

KW - Convolutional neural network (CNN)

KW - Generative adversarial network (GAN)

KW - Projection-based mixed reality

UR - http://www.scopus.com/inward/record.url?scp=85081951806&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85081951806&partnerID=8YFLogxK

U2 - 10.1109/GCCE46687.2019.9015415

DO - 10.1109/GCCE46687.2019.9015415

M3 - Conference contribution

AN - SCOPUS:85081951806

T3 - 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019

SP - 227

EP - 228

BT - 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 8th IEEE Global Conference on Consumer Electronics, GCCE 2019

Y2 - 15 October 2019 through 18 October 2019

ER -

Generative adversarial network based image blur compensation for projection-based mixed reality

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this