Details

Autor(en) / Beteiligte

• Arad, Boaz
• Timofte, Radu
• Ben-Shahar, Ohad
• Lin, Yi-Tun
• Finlayson, Graham
• Givati, Shai
• Li, Jiaojiao
• Wu, Chaoxiong
• Song, Rui
• Li, Yunsong
• Liu, Fei
• Lang, Zhiqiang
• Wei, Wei
• Zhang, Lei
• Nie, Jiangtao
• Zhao, Yuzhi
• Po, Lai-Man
• Yan, Qiong
• Liu, Wei
• Lin, Tingyu
• Kim, Youngjung
• Shin, Changyeop
• Rho, Kyeongha
• Kim, Sungho
• ZHU, Zhiyu
• HOU, Junhui
• Sun, He
• Ren, Jinchang
• Fang, Zhenyu
• Yan, Yijun
• Peng, Hao
• Chen, Xiaomei
• Zhao, Jie
• Stiebel, Tarek
• Koppers, Simon
• Merhof, Dorit
• Gupta, Honey
• Mitra, Kaushik
• Fubara, Biebele Joslyn
• Sedky, Mohamed
• Dyke, Dave
• Banerjee, Atmadeep
• Palrecha, Akash
• sabarinathan, Sabarinathan
• Uma, K
• Vinothini, D Synthiya
• Sathya Bama, B
• Md Mansoor Roomi, S M

Titel

NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image

Ist Teil von

• 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020, p.1806-1822

Ort / Verlag

IEEE

Erscheinungsjahr

2020

Quelle

IEEE/IET Electronic Library (IEL)

Beschreibungen/Notizen

• 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.