Visual Computing Group

NTIRE 2022 Spectral Recovery Challenge and Data Set

Arad B, Timofte R, Yahel R, Morag N, Bernat A, Cai Y, Lin J, Lin Z, Wang H, Zhang Y, Pfister H, Van Gool L, Liu S, Li Y, Feng C, Lei L, Li J, Du S, Wu C, Leng Y, Song R, Zhang M, Song C, Zhao S, Lang Z, Wei W, Zhang L, Dian R, Shan T, Guo A, Feng C, Liu J, Agarla M, Bianco S, Buzzelli M, Celona L, Schettini R, He J, Xiao Y, Xiao J, Yuan Q, Li J, Zhang L, Kwon T, Ryu D, Bae H, Yang H, Chang H, Huang Z, Chen W, Kuo S, Chen J, Li H, Liu S, Sabarinathan, Uma K, Bama BS, and Roomi SMM.

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022.

This paper reviews the third biennial challenge on spectral reconstruction from RGB images, i.e., the recovery of whole-scene hyperspectral (HS) information from a 3-channel RGB image. This challenge presents the "ARAD_1K" data set: a new, larger-than-ever natural hyperspectral image data set containing 1,000 images. Challenge participants were required to recover hyperspectral information from synthetically generated JPEG-compressed RGB images simulating capture by a known calibrated camera, operating under partially known parameters, in a setting which includes acquisition noise. The challenge was attended by 241 teams, with 60 teams competing in the final testing phase, 12 of which provided detailed descriptions of their methodology which are included in this report. The performance of these submissions is reviewed and provided here as a gauge for the current state-of-the-art in spectral reconstruction from natural RGB images.

Acknowledgements

We thank the NTIRE 2022 sponsors: Huawei, Reality Labs, Bending Spoons, MediaTek, OPPO, Oddity, Voyage81, ETH Zurich (Computer Vision Lab) and University of Wurzburg (CAIDAS).

Material

Paper

Citation

@InProceedings {arad2022ntire,
    title={NTIRE 2022 Spectral Recovery Challenge and Data Set},
    author={Arad, Boaz and Timofte, Radu and Yahel, Rony and Morag, Nimrod and Bernat, Amir and Cai, Yuanhao and Lin, Jing and Lin, Zudi and Wang, Haoqian and Zhang, Yulun and Pfister, Hanspeter and Van Gool, Luc and Liu, Shuai and Li, Yongqiang and Feng, Chaoyu and Lei, Lei and Li, Jiaojiao and Du, Songcheng and Wu, Chaoxiong and Leng, Yihong and Song, Rui and Zhang, Mingwei and Song, Chongxing and Zhao, Shuyi and Lang, Zhiqiang and Wei, Wei and Zhang, Lei and Dian, Renwei and Shan, Tianci and Guo, Anjing and Feng, Chengguo and Liu, Jinyang and Agarla, Mirko and Bianco, Simone and Buzzelli, Marco and Celona, Luigi and Schettini, Raimondo and He, Jiang and Xiao, Yi and Xiao, Jiajun and Yuan, Qiangqiang and Li, Jie and Zhang, Liangpei and Kwon, Taesung and Ryu, Dohoon and Bae, Hyokyoung and Yang, Hao-Hsiang and Chang, Hua-En and Huang, Zhi-Kai and Chen, Wei-Ting and Kuo, Sy-Yen and Chen, Junyu and Li, Haiwei and Liu, Song and Sabarinathan and Uma, K and Bama, B Sathya and Roomi, S. Mohamed Mansoor},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
    month={June},
    year={2022},
    pages={863--881}
}

BibTex