NTIRE 2020 challenge on spectral reconstruction from an RGB image

Arad B, Timofte R, Ben-Shahar O, Lin YT, Finlayson G, Givati S, Li J, Wu C, Song R, Li Y, Liu F, Lang Z, Wei W, Zhang L, Nie J, Zhao Y, Po LM, Yan Q, Liu W, Lin T, Kim Y, Shin C, Rho K, Kim S, Zhu Z, Hou J, Sun H, Ren J, Fang Z, Yan Y, Peng H, Chen X, Zhao J, Stiebel T, Koppers S, Merhof D, Gupta H, Mitra K, Fubara BJ, Sedky M, Dyke D, Banerjee A, Palrecha A, Sabarinathan , Uma K, Vinothini DS, Bama BS, Roomi SMMM (2020)

Publication Type: Conference contribution

Publication year: 2020

Publisher: IEEE Computer Society

Book Volume: 2020-June

Pages Range: 1806-1822

Conference Proceedings Title: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

Event location: Virtual, Online, USA

ISBN: 9781728193601

DOI: 10.1109/CVPRW50498.2020.00231

Abstract

This paper reviews the second challenge on spectral reconstruction from RGB images, i.e., the recovery of whole- scene hyperspectral (HS) information from a 3-channel RGB image. As in the previous challenge, two tracks were provided: (i) a "Clean" track where HS images are estimated from noise-free RGBs, the RGB images are themselves calculated numerically using the ground-truth HS images and supplied spectral sensitivity functions (ii) a "Real World" track, simulating capture by an uncalibrated and unknown camera, where the HS images are recovered from noisy JPEG-compressed RGB images. A new, larger-than-ever, natural hyperspectral image data set is presented, containing a total of 510 HS images. The Clean and Real World tracks had 103 and 78 registered participants respectively, with 14 teams competing in the final testing phase. A description of the proposed methods, alongside their challenge scores and an extensive evaluation of top performing methods is also provided. They gauge the state-of-the-art in spectral reconstruction from an RGB image.

Involved external institutions

Voyage81 IL Israel (IL) Xidian University CN China (CN) Northwestern Polytechnical University / 西北工业大学 (NPU/NWPU) CN China (CN) City University of Hong Kong (CityU) CN China (CN) SenseTime / 商汤科技 HK Hong Kong (HK) University of Strathclyde GB United Kingdom (GB) Beijing Institute of Technology (BIT) / 北京理工大学 CN China (CN) Rheinisch-Westfälische Technische Hochschule (RWTH) Aachen DE Germany (DE) Eidgenössische Technische Hochschule Zürich (ETHZ) / Swiss Federal Institute of Technology in Zurich CH Switzerland (CH) Ben-Gurion University of the Negev (BGU) / אוניברסיטת בן-גוריון בנגב IL Israel (IL) University of East Anglia GB United Kingdom (GB) Agency for Defense Development (ADD) / 국방과학연구소 KR Korea, Republic of (KR) Staffordshire University DE Germany (DE) Thiagarajar College of Engineering (TCE) IN India (IN) Indian Institute of Technology Madras IN India (IN) Pixxel IN India (IN) Couger Inc. JP Japan (JP)

How to cite

APA:

Arad, B., Timofte, R., Ben-Shahar, O., Lin, Y.-T., Finlayson, G., Givati, S.,... Roomi, S.M.M.M. (2020). NTIRE 2020 challenge on spectral reconstruction from an RGB image. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (pp. 1806-1822). Virtual, Online, USA: IEEE Computer Society.

MLA:

Arad, Boaz, et al. "NTIRE 2020 challenge on spectral reconstruction from an RGB image." Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020, Virtual, Online, USA IEEE Computer Society, 2020. 1806-1822.

BibTeX: Download