TY - GEN
T1 - Reconstructing Hyperspectral Images from RGB Inputs Based on Intrinsic Image Decomposition
AU - Wang, Nan
AU - Mei, Shaohui
AU - Zhang, Yifan
AU - Zhang, Bowei
AU - Ma, Mingyang
AU - Zhang, Xiangqing
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Spectral super-resolution (SR), which generally reconstructs hyperspectral images (HSIs) from RGB inputs, has attracted lots of attention recently. In this paper, a spectral SR algorithm based on intrinsic image decomposition (IID) is proposed, in which RGB images are decomposed into reflectance images and shading images to fully explore RGB features for HSI reconstruction. Considering that features of the reflectance image are only related to the material of objects, the sparsity of material reflectivity is used to reconstruct the reflectance image of HSI. Moreover, an convonlutional neural network (CNN) is constructed to reconstruct shading parts of HSI. Finally, these two reconstructed results are fused to generate the high spectral resolution HSI and an enhancement network is also designed to further improve the recontruction performance. Experimental results with two benchmark datasets, ICVL and CAVE, demonstrate that the performance of the proposed algorithm is superior to several state-of-the-art spectral SR algorithms.
AB - Spectral super-resolution (SR), which generally reconstructs hyperspectral images (HSIs) from RGB inputs, has attracted lots of attention recently. In this paper, a spectral SR algorithm based on intrinsic image decomposition (IID) is proposed, in which RGB images are decomposed into reflectance images and shading images to fully explore RGB features for HSI reconstruction. Considering that features of the reflectance image are only related to the material of objects, the sparsity of material reflectivity is used to reconstruct the reflectance image of HSI. Moreover, an convonlutional neural network (CNN) is constructed to reconstruct shading parts of HSI. Finally, these two reconstructed results are fused to generate the high spectral resolution HSI and an enhancement network is also designed to further improve the recontruction performance. Experimental results with two benchmark datasets, ICVL and CAVE, demonstrate that the performance of the proposed algorithm is superior to several state-of-the-art spectral SR algorithms.
KW - Convolutional neural network
KW - Hyperspectral
KW - Intrinsic image decomposition
KW - Super-resolution
UR - http://www.scopus.com/inward/record.url?scp=85140367235&partnerID=8YFLogxK
U2 - 10.1109/IGARSS46834.2022.9883751
DO - 10.1109/IGARSS46834.2022.9883751
M3 - 会议稿件
AN - SCOPUS:85140367235
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 2374
EP - 2377
BT - IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022
Y2 - 17 July 2022 through 22 July 2022
ER -