NTIRE 2018 challenge on spectral reconstruction from RGB images

Boaz Arad, Ohad Ben-Shahar, Radu Timofte, Luc Van Gool, Lei Zhang, Ming Hsuan Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

This paper reviews the first challenge on spectral image reconstruction from RGB images, i.e., the recovery of whole-scene hyperspectral (HS) information from a 3-channel RGB image. The challenge was divided into 2 tracks: the 'Clean' track sought HS recovery from noiseless RGB images obtained from a known response function (representing spectrally-calibrated camera) while the 'Real World' track challenged participants to recover HS cubes from JPEG-compressed RGB images generated by an unknown response function. To facilitate the challenge, the BGU Hyperspectral Image Database [4] was extended to provide participants with 256 natural HS training images, and 5+10 additional images for validation and testing, respectively. The 'Clean' and 'Real World' tracks had 73 and 63 registered participants respectively, with 12 teams competing in the final testing phase. Proposed methods and their corresponding results are reported in this review.

Original languageEnglish
Title of host publicationProceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
PublisherIEEE Computer Society
Pages1042-1051
Number of pages10
ISBN (Electronic)9781538661000
DOIs
Publication statusPublished - 2018 Dec 13
Event31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 - Salt Lake City, United States
Duration: 2018 Jun 182018 Jun 22

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume2018-June
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Other

Other31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
CountryUnited States
CitySalt Lake City
Period18/6/1818/6/22

Fingerprint

Recovery
Testing
Image reconstruction
Cameras

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Arad, B., Ben-Shahar, O., Timofte, R., Van Gool, L., Zhang, L., & Yang, M. H. (2018). NTIRE 2018 challenge on spectral reconstruction from RGB images. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 (pp. 1042-1051). [8575291] (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2018-June). IEEE Computer Society. https://doi.org/10.1109/CVPRW.2018.00138
Arad, Boaz ; Ben-Shahar, Ohad ; Timofte, Radu ; Van Gool, Luc ; Zhang, Lei ; Yang, Ming Hsuan. / NTIRE 2018 challenge on spectral reconstruction from RGB images. Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. IEEE Computer Society, 2018. pp. 1042-1051 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).
@inproceedings{94d63758613e40089567014d41cff29d,
title = "NTIRE 2018 challenge on spectral reconstruction from RGB images",
abstract = "This paper reviews the first challenge on spectral image reconstruction from RGB images, i.e., the recovery of whole-scene hyperspectral (HS) information from a 3-channel RGB image. The challenge was divided into 2 tracks: the 'Clean' track sought HS recovery from noiseless RGB images obtained from a known response function (representing spectrally-calibrated camera) while the 'Real World' track challenged participants to recover HS cubes from JPEG-compressed RGB images generated by an unknown response function. To facilitate the challenge, the BGU Hyperspectral Image Database [4] was extended to provide participants with 256 natural HS training images, and 5+10 additional images for validation and testing, respectively. The 'Clean' and 'Real World' tracks had 73 and 63 registered participants respectively, with 12 teams competing in the final testing phase. Proposed methods and their corresponding results are reported in this review.",
author = "Boaz Arad and Ohad Ben-Shahar and Radu Timofte and {Van Gool}, Luc and Lei Zhang and Yang, {Ming Hsuan}",
year = "2018",
month = "12",
day = "13",
doi = "10.1109/CVPRW.2018.00138",
language = "English",
series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",
publisher = "IEEE Computer Society",
pages = "1042--1051",
booktitle = "Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018",
address = "United States",

}

Arad, B, Ben-Shahar, O, Timofte, R, Van Gool, L, Zhang, L & Yang, MH 2018, NTIRE 2018 challenge on spectral reconstruction from RGB images. in Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018., 8575291, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2018-June, IEEE Computer Society, pp. 1042-1051, 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018, Salt Lake City, United States, 18/6/18. https://doi.org/10.1109/CVPRW.2018.00138

NTIRE 2018 challenge on spectral reconstruction from RGB images. / Arad, Boaz; Ben-Shahar, Ohad; Timofte, Radu; Van Gool, Luc; Zhang, Lei; Yang, Ming Hsuan.

Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. IEEE Computer Society, 2018. p. 1042-1051 8575291 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2018-June).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - NTIRE 2018 challenge on spectral reconstruction from RGB images

AU - Arad, Boaz

AU - Ben-Shahar, Ohad

AU - Timofte, Radu

AU - Van Gool, Luc

AU - Zhang, Lei

AU - Yang, Ming Hsuan

PY - 2018/12/13

Y1 - 2018/12/13

N2 - This paper reviews the first challenge on spectral image reconstruction from RGB images, i.e., the recovery of whole-scene hyperspectral (HS) information from a 3-channel RGB image. The challenge was divided into 2 tracks: the 'Clean' track sought HS recovery from noiseless RGB images obtained from a known response function (representing spectrally-calibrated camera) while the 'Real World' track challenged participants to recover HS cubes from JPEG-compressed RGB images generated by an unknown response function. To facilitate the challenge, the BGU Hyperspectral Image Database [4] was extended to provide participants with 256 natural HS training images, and 5+10 additional images for validation and testing, respectively. The 'Clean' and 'Real World' tracks had 73 and 63 registered participants respectively, with 12 teams competing in the final testing phase. Proposed methods and their corresponding results are reported in this review.

AB - This paper reviews the first challenge on spectral image reconstruction from RGB images, i.e., the recovery of whole-scene hyperspectral (HS) information from a 3-channel RGB image. The challenge was divided into 2 tracks: the 'Clean' track sought HS recovery from noiseless RGB images obtained from a known response function (representing spectrally-calibrated camera) while the 'Real World' track challenged participants to recover HS cubes from JPEG-compressed RGB images generated by an unknown response function. To facilitate the challenge, the BGU Hyperspectral Image Database [4] was extended to provide participants with 256 natural HS training images, and 5+10 additional images for validation and testing, respectively. The 'Clean' and 'Real World' tracks had 73 and 63 registered participants respectively, with 12 teams competing in the final testing phase. Proposed methods and their corresponding results are reported in this review.

UR - http://www.scopus.com/inward/record.url?scp=85060849728&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060849728&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2018.00138

DO - 10.1109/CVPRW.2018.00138

M3 - Conference contribution

AN - SCOPUS:85060849728

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 1042

EP - 1051

BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018

PB - IEEE Computer Society

ER -

Arad B, Ben-Shahar O, Timofte R, Van Gool L, Zhang L, Yang MH. NTIRE 2018 challenge on spectral reconstruction from RGB images. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. IEEE Computer Society. 2018. p. 1042-1051. 8575291. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). https://doi.org/10.1109/CVPRW.2018.00138