Home > Research > Publications & Outputs > Automatic noise modeling for ghost-free HDR rec...
View graph of relations

Automatic noise modeling for ghost-free HDR reconstruction

Research output: Contribution to journalJournal article

Published

Standard

Automatic noise modeling for ghost-free HDR reconstruction. / Granados, Miguel; Kim, Kwang In; Tompkin, James; Theobalt, Christian.

In: ACM Transactions on Graphics, Vol. 32, No. 6, 11.2013, p. 201:1-201:10.

Research output: Contribution to journalJournal article

Harvard

Granados, M, Kim, KI, Tompkin, J & Theobalt, C 2013, 'Automatic noise modeling for ghost-free HDR reconstruction', ACM Transactions on Graphics, vol. 32, no. 6, pp. 201:1-201:10. https://doi.org/10.1145/2508363.2508410

APA

Granados, M., Kim, K. I., Tompkin, J., & Theobalt, C. (2013). Automatic noise modeling for ghost-free HDR reconstruction. ACM Transactions on Graphics, 32(6), 201:1-201:10. https://doi.org/10.1145/2508363.2508410

Vancouver

Granados M, Kim KI, Tompkin J, Theobalt C. Automatic noise modeling for ghost-free HDR reconstruction. ACM Transactions on Graphics. 2013 Nov;32(6):201:1-201:10. https://doi.org/10.1145/2508363.2508410

Author

Granados, Miguel ; Kim, Kwang In ; Tompkin, James ; Theobalt, Christian. / Automatic noise modeling for ghost-free HDR reconstruction. In: ACM Transactions on Graphics. 2013 ; Vol. 32, No. 6. pp. 201:1-201:10.

Bibtex

@article{ae71167ab5cf427a9a63e9963482fd49,
title = "Automatic noise modeling for ghost-free HDR reconstruction",
abstract = "High dynamic range reconstruction of dynamic scenes requires careful handling of dynamic objects to prevent ghosting. However, in a recent review, Srikantha et al. [2012] conclude that {"}there is no single best method and the selection of an approach depends on the user's goal{"}. We attempt to solve this problem with a novel approach that models the noise distribution of color values. We estimate the likelihood that a pair of colors in different images are observations of the same irradiance, and we use a Markov random field prior to reconstruct irradiance from pixels that are likely to correspond to the same static scene object. Dynamic content is handled by selecting a single low dynamic range source image and hand-held capture is supported through homography-based image alignment. Our noise-based reconstruction method achieves better ghost detection and removal than state-of-the-art methods for cluttered scenes with large object displacements. As such, our method is broadly applicable and helps move the field towards a single method for dynamic scene HDR reconstruction.",
author = "Miguel Granados and Kim, {Kwang In} and James Tompkin and Christian Theobalt",
year = "2013",
month = nov,
doi = "10.1145/2508363.2508410",
language = "English",
volume = "32",
pages = "201:1--201:10",
journal = "ACM Transactions on Graphics",
issn = "0730-0301",
publisher = "Association for Computing Machinery (ACM)",
number = "6",

}

RIS

TY - JOUR

T1 - Automatic noise modeling for ghost-free HDR reconstruction

AU - Granados, Miguel

AU - Kim, Kwang In

AU - Tompkin, James

AU - Theobalt, Christian

PY - 2013/11

Y1 - 2013/11

N2 - High dynamic range reconstruction of dynamic scenes requires careful handling of dynamic objects to prevent ghosting. However, in a recent review, Srikantha et al. [2012] conclude that "there is no single best method and the selection of an approach depends on the user's goal". We attempt to solve this problem with a novel approach that models the noise distribution of color values. We estimate the likelihood that a pair of colors in different images are observations of the same irradiance, and we use a Markov random field prior to reconstruct irradiance from pixels that are likely to correspond to the same static scene object. Dynamic content is handled by selecting a single low dynamic range source image and hand-held capture is supported through homography-based image alignment. Our noise-based reconstruction method achieves better ghost detection and removal than state-of-the-art methods for cluttered scenes with large object displacements. As such, our method is broadly applicable and helps move the field towards a single method for dynamic scene HDR reconstruction.

AB - High dynamic range reconstruction of dynamic scenes requires careful handling of dynamic objects to prevent ghosting. However, in a recent review, Srikantha et al. [2012] conclude that "there is no single best method and the selection of an approach depends on the user's goal". We attempt to solve this problem with a novel approach that models the noise distribution of color values. We estimate the likelihood that a pair of colors in different images are observations of the same irradiance, and we use a Markov random field prior to reconstruct irradiance from pixels that are likely to correspond to the same static scene object. Dynamic content is handled by selecting a single low dynamic range source image and hand-held capture is supported through homography-based image alignment. Our noise-based reconstruction method achieves better ghost detection and removal than state-of-the-art methods for cluttered scenes with large object displacements. As such, our method is broadly applicable and helps move the field towards a single method for dynamic scene HDR reconstruction.

U2 - 10.1145/2508363.2508410

DO - 10.1145/2508363.2508410

M3 - Journal article

VL - 32

SP - 201:1-201:10

JO - ACM Transactions on Graphics

JF - ACM Transactions on Graphics

SN - 0730-0301

IS - 6

ER -