Variational Shape from Light Field

Stefan Heber, Rene Ranftl, Thomas Pock

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Abstract

In this paper we propose an efficient method to calculate a high-quality depth map from a single raw image captured by a light field or plenoptic camera. The proposed model combines the main idea of Active Wavefront Sampling (AWS) with the light field technique, i.e. we extract so-called sub-aperture images out of the raw image of a plenoptic camera, in such a way that the virtual view points are arranged on circles around a fixed center view. By tracking an imaged scene point over a sequence of sub-aperture images corresponding to a common circle, one can observe a virtual rotation of the scene point on the image plane. Our model is able to measure a dense field of these rotations, which are inversely related to the scene depth.
Original languageEnglish
Title of host publicationEnergy Minimization Methods in Computer Vision and Pattern Recognition
Subtitle of host publication9th International Conference, EMMCVPR 2013, Lund, Sweden, August 19-21, 2013. Proceedings
PublisherSpringer Berlin - Heidelberg
Pages66-79
Volume8081
ISBN (Electronic)978-3-642-40395-8
ISBN (Print)978-3-642-40394-1
DOIs
Publication statusAccepted/In press - 2013

Fingerprint

Cameras
Wavefronts
Sampling

Cite this

Heber, S., Ranftl, R., & Pock, T. (Accepted/In press). Variational Shape from Light Field. In Energy Minimization Methods in Computer Vision and Pattern Recognition: 9th International Conference, EMMCVPR 2013, Lund, Sweden, August 19-21, 2013. Proceedings (Vol. 8081, pp. 66-79). Springer Berlin - Heidelberg. https://doi.org/10.1007/978-3-642-40395-8_6

Variational Shape from Light Field. / Heber, Stefan; Ranftl, Rene; Pock, Thomas.

Energy Minimization Methods in Computer Vision and Pattern Recognition: 9th International Conference, EMMCVPR 2013, Lund, Sweden, August 19-21, 2013. Proceedings. Vol. 8081 Springer Berlin - Heidelberg, 2013. p. 66-79.

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Heber, S, Ranftl, R & Pock, T 2013, Variational Shape from Light Field. in Energy Minimization Methods in Computer Vision and Pattern Recognition: 9th International Conference, EMMCVPR 2013, Lund, Sweden, August 19-21, 2013. Proceedings. vol. 8081, Springer Berlin - Heidelberg, pp. 66-79. https://doi.org/10.1007/978-3-642-40395-8_6
Heber S, Ranftl R, Pock T. Variational Shape from Light Field. In Energy Minimization Methods in Computer Vision and Pattern Recognition: 9th International Conference, EMMCVPR 2013, Lund, Sweden, August 19-21, 2013. Proceedings. Vol. 8081. Springer Berlin - Heidelberg. 2013. p. 66-79 https://doi.org/10.1007/978-3-642-40395-8_6
Heber, Stefan ; Ranftl, Rene ; Pock, Thomas. / Variational Shape from Light Field. Energy Minimization Methods in Computer Vision and Pattern Recognition: 9th International Conference, EMMCVPR 2013, Lund, Sweden, August 19-21, 2013. Proceedings. Vol. 8081 Springer Berlin - Heidelberg, 2013. pp. 66-79
@inproceedings{c8d78457c55144769f72f91979e426bb,
title = "Variational Shape from Light Field",
abstract = "In this paper we propose an efficient method to calculate a high-quality depth map from a single raw image captured by a light field or plenoptic camera. The proposed model combines the main idea of Active Wavefront Sampling (AWS) with the light field technique, i.e. we extract so-called sub-aperture images out of the raw image of a plenoptic camera, in such a way that the virtual view points are arranged on circles around a fixed center view. By tracking an imaged scene point over a sequence of sub-aperture images corresponding to a common circle, one can observe a virtual rotation of the scene point on the image plane. Our model is able to measure a dense field of these rotations, which are inversely related to the scene depth.",
author = "Stefan Heber and Rene Ranftl and Thomas Pock",
year = "2013",
doi = "10.1007/978-3-642-40395-8_6",
language = "English",
isbn = "978-3-642-40394-1",
volume = "8081",
pages = "66--79",
booktitle = "Energy Minimization Methods in Computer Vision and Pattern Recognition",
publisher = "Springer Berlin - Heidelberg",

}

TY - GEN

T1 - Variational Shape from Light Field

AU - Heber, Stefan

AU - Ranftl, Rene

AU - Pock, Thomas

PY - 2013

Y1 - 2013

N2 - In this paper we propose an efficient method to calculate a high-quality depth map from a single raw image captured by a light field or plenoptic camera. The proposed model combines the main idea of Active Wavefront Sampling (AWS) with the light field technique, i.e. we extract so-called sub-aperture images out of the raw image of a plenoptic camera, in such a way that the virtual view points are arranged on circles around a fixed center view. By tracking an imaged scene point over a sequence of sub-aperture images corresponding to a common circle, one can observe a virtual rotation of the scene point on the image plane. Our model is able to measure a dense field of these rotations, which are inversely related to the scene depth.

AB - In this paper we propose an efficient method to calculate a high-quality depth map from a single raw image captured by a light field or plenoptic camera. The proposed model combines the main idea of Active Wavefront Sampling (AWS) with the light field technique, i.e. we extract so-called sub-aperture images out of the raw image of a plenoptic camera, in such a way that the virtual view points are arranged on circles around a fixed center view. By tracking an imaged scene point over a sequence of sub-aperture images corresponding to a common circle, one can observe a virtual rotation of the scene point on the image plane. Our model is able to measure a dense field of these rotations, which are inversely related to the scene depth.

U2 - 10.1007/978-3-642-40395-8_6

DO - 10.1007/978-3-642-40395-8_6

M3 - Conference contribution

SN - 978-3-642-40394-1

VL - 8081

SP - 66

EP - 79

BT - Energy Minimization Methods in Computer Vision and Pattern Recognition

PB - Springer Berlin - Heidelberg

ER -