4D light field segmentation with spatial and angular consistencies

Hajime Mihara; Takuya Funatomi; Kenichiro Tanaka; Hiroyuki Kubo; Yasuhiro Mukaigawa; Hajime Nagahara

doi:10.1109/ICCPHOT.2016.7492872

4D light field segmentation with spatial and angular consistencies

Hajime Mihara, Takuya Funatomi, Kenichiro Tanaka, Hiroyuki Kubo, Yasuhiro Mukaigawa, Hajime Nagahara

Real world robotics

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

24 Citations (Scopus)

Abstract

In this paper, we describe a supervised four-dimensional (4D) light field segmentation method that uses a graph-cut algorithm. Since 4D light field data has implicit depth information and contains redundancy, it differs from simple 4D hyper-volume. In order to preserve redundancy, we define two neighboring ray types (spatial and angular) in light field data. To obtain higher segmentation accuracy, we also design a learning-based likelihood, called objectness, which utilizes appearance and disparity cues. We show the effectiveness of our method via numerical evaluation and some light field editing applications using both synthetic and real-world light fields.

Original language	English
Title of host publication	2016 IEEE International Conference on Computational Photography, ICCP 2016 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781467386234
DOIs	https://doi.org/10.1109/ICCPHOT.2016.7492872
Publication status	Published - Jun 15 2016
Event	2016 IEEE International Conference on Computational Photography, ICCP 2016 - Evanston, United States Duration: May 13 2016 → May 15 2016

Publication series

Name	2016 IEEE International Conference on Computational Photography, ICCP 2016 - Proceedings

Other

Other	2016 IEEE International Conference on Computational Photography, ICCP 2016
Country/Territory	United States
City	Evanston
Period	5/13/16 → 5/15/16

All Science Journal Classification (ASJC) codes

Media Technology
Instrumentation

Access to Document

10.1109/ICCPHOT.2016.7492872

Cite this

Mihara, H., Funatomi, T., Tanaka, K., Kubo, H., Mukaigawa, Y., & Nagahara, H. (2016). 4D light field segmentation with spatial and angular consistencies. In 2016 IEEE International Conference on Computational Photography, ICCP 2016 - Proceedings [7492872] (2016 IEEE International Conference on Computational Photography, ICCP 2016 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCPHOT.2016.7492872

4D light field segmentation with spatial and angular consistencies. / Mihara, Hajime; Funatomi, Takuya; Tanaka, Kenichiro et al.

2016 IEEE International Conference on Computational Photography, ICCP 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. 7492872 (2016 IEEE International Conference on Computational Photography, ICCP 2016 - Proceedings).

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

Mihara, H, Funatomi, T, Tanaka, K, Kubo, H, Mukaigawa, Y & Nagahara, H 2016, 4D light field segmentation with spatial and angular consistencies. in 2016 IEEE International Conference on Computational Photography, ICCP 2016 - Proceedings., 7492872, 2016 IEEE International Conference on Computational Photography, ICCP 2016 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2016 IEEE International Conference on Computational Photography, ICCP 2016, Evanston, United States, 5/13/16. https://doi.org/10.1109/ICCPHOT.2016.7492872

Mihara H, Funatomi T, Tanaka K, Kubo H, Mukaigawa Y, Nagahara H. 4D light field segmentation with spatial and angular consistencies. In 2016 IEEE International Conference on Computational Photography, ICCP 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2016. 7492872. (2016 IEEE International Conference on Computational Photography, ICCP 2016 - Proceedings). doi: 10.1109/ICCPHOT.2016.7492872

Mihara, Hajime ; Funatomi, Takuya ; Tanaka, Kenichiro et al. / 4D light field segmentation with spatial and angular consistencies. 2016 IEEE International Conference on Computational Photography, ICCP 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. (2016 IEEE International Conference on Computational Photography, ICCP 2016 - Proceedings).

@inproceedings{6975bb937f344d8392f1ae1b9efd9626,

title = "4D light field segmentation with spatial and angular consistencies",

abstract = "In this paper, we describe a supervised four-dimensional (4D) light field segmentation method that uses a graph-cut algorithm. Since 4D light field data has implicit depth information and contains redundancy, it differs from simple 4D hyper-volume. In order to preserve redundancy, we define two neighboring ray types (spatial and angular) in light field data. To obtain higher segmentation accuracy, we also design a learning-based likelihood, called objectness, which utilizes appearance and disparity cues. We show the effectiveness of our method via numerical evaluation and some light field editing applications using both synthetic and real-world light fields.",

author = "Hajime Mihara and Takuya Funatomi and Kenichiro Tanaka and Hiroyuki Kubo and Yasuhiro Mukaigawa and Hajime Nagahara",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 IEEE International Conference on Computational Photography, ICCP 2016 ; Conference date: 13-05-2016 Through 15-05-2016",

year = "2016",

month = jun,

day = "15",

doi = "10.1109/ICCPHOT.2016.7492872",

language = "English",

series = "2016 IEEE International Conference on Computational Photography, ICCP 2016 - Proceedings",

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

booktitle = "2016 IEEE International Conference on Computational Photography, ICCP 2016 - Proceedings",

address = "United States",

}

TY - GEN

T1 - 4D light field segmentation with spatial and angular consistencies

AU - Mihara, Hajime

AU - Funatomi, Takuya

AU - Tanaka, Kenichiro

AU - Kubo, Hiroyuki

AU - Mukaigawa, Yasuhiro

AU - Nagahara, Hajime

PY - 2016/6/15

Y1 - 2016/6/15

N2 - In this paper, we describe a supervised four-dimensional (4D) light field segmentation method that uses a graph-cut algorithm. Since 4D light field data has implicit depth information and contains redundancy, it differs from simple 4D hyper-volume. In order to preserve redundancy, we define two neighboring ray types (spatial and angular) in light field data. To obtain higher segmentation accuracy, we also design a learning-based likelihood, called objectness, which utilizes appearance and disparity cues. We show the effectiveness of our method via numerical evaluation and some light field editing applications using both synthetic and real-world light fields.

AB - In this paper, we describe a supervised four-dimensional (4D) light field segmentation method that uses a graph-cut algorithm. Since 4D light field data has implicit depth information and contains redundancy, it differs from simple 4D hyper-volume. In order to preserve redundancy, we define two neighboring ray types (spatial and angular) in light field data. To obtain higher segmentation accuracy, we also design a learning-based likelihood, called objectness, which utilizes appearance and disparity cues. We show the effectiveness of our method via numerical evaluation and some light field editing applications using both synthetic and real-world light fields.

UR - http://www.scopus.com/inward/record.url?scp=84979671168&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84979671168&partnerID=8YFLogxK

U2 - 10.1109/ICCPHOT.2016.7492872

DO - 10.1109/ICCPHOT.2016.7492872

M3 - Conference contribution

AN - SCOPUS:84979671168

T3 - 2016 IEEE International Conference on Computational Photography, ICCP 2016 - Proceedings

BT - 2016 IEEE International Conference on Computational Photography, ICCP 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 IEEE International Conference on Computational Photography, ICCP 2016

Y2 - 13 May 2016 through 15 May 2016

ER -

4D light field segmentation with spatial and angular consistencies

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this