NTIRE 2018 Challenge on Spectral Reconstruction from RGB Images

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 obta...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) s. 1042 - 104209
Hlavní autoři: Arad, Boaz, Liu, Dong, Wu, Feng, Lanaras, Charis, Galliani, Silvano, Schindler, Konrad, Stiebel, Tarek, Koppers, Simon, Seltsam, Philipp, Zhou, Ruofan, El Helou, Majed, Ben-Shahar, Ohad, Lahoud, Fayez, Shahpaski, Marjan, Zheng, Ke, Gao, Lianru, Zhang, Bing, Cui, Ximin, Yu, Haoyang, Can, Yigit Baran, Alvarez-Gila, Aitor, van de Weijer, Joost, Timofte, Radu, Garrote, Estibaliz, Galdran, Adrian, Sharma, Manoj, Koundinya, Sriharsha, Upadhyay, Avinash, Manekar, Raunak, Mukhopadhyay, Rudrabha, Sharma, Himanshu, Chaudhury, Santanu, Nagasubramanian, Koushik, Van Gool, Luc, Ghosal, Sambuddha, Singh, Asheesh K., Singh, Arti, Ganapathysubramanian, Baskar, Sarkar, Soumik, Zhang, Lei, Yang, Ming-Hsuan, Xiong, Zhiwei, Chen, Chang, Shi, Zhan
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2018
Témata:
Cameras
Hyperspectral imaging
Image reconstruction
Neural networks
Runtime
Training
ISSN:2160-7516
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
ISSN:2160-7516
DOI:10.1109/CVPRW.2018.00138