Hyperspectral Image Super-Resolution in Arbitrary Input-Output Band Settings
Hyperspectral Image Super-Resolution in Arbitrary Input-Output Band Settings
复制标题
DOI：
10.1109/wacvw54805.2022.00082
复制
发表时间：
2021-03
期刊：
影响因子：
--
通讯作者：
Zhongyang Zhang;Zhiyang Xu;Zia U. Ahmed;Asif Salekin;Tauhidur Rahman
中科院分区：
文献类型：
--
作者：
Zhongyang Zhang;Zhiyang Xu;Zia U. Ahmed;Asif Salekin;Tauhidur Rahman
窄光谱波段的高光谱图像能够获取丰富的光谱信息，但在获取过程中牺牲了高光谱图像的空间分辨率。近年来，许多基于机器学习的HSI超分辨率（SR）算法被提出。然而，这些方法的基本限制之一是它们高度依赖于图像和相机设置，并且只能学习将具有一个特定设置的输入HSI映射到具有另一个特定设置的输出HSI。然而，由于HSI相机的多样性，不同相机捕获的图像具有不同的光谱响应函数和波段数。因此，现有的基于机器学习的方法无法学习针对各种各样的输入-输出频带设置来超分辨HSI。我们提出了一个单一的基于元学习的超分辨率（MLSR）模型，该模型可以在任意数量的输入波段的峰值波长的HSI图像，并生成具有任意数量的输出波段的峰值波长的SR HSI。我们利用NTIRE 2020和ICVL数据集来训练和验证MLSR模型的性能。结果表明，该模型可以在任意输入输出波段设置下成功地产生超分辨HSI波段。结果更好，或者至少与在特定输入-输出带设置上单独训练的基线相当。
Hyperspectral image (HSI) with narrow spectral bands can capture rich spectral information, but it sacrifices its spatial resolution in the process. Many machine-learning-based HSI super-resolution (SR) algorithms have been proposed recently. However, one of the fundamental limitations of these approaches is that they are highly dependent on image and camera settings and can only learn to map an input HSI with one specific setting to an output HSI with another. However, different cameras capture images with different spectral response functions and bands numbers due to the diversity of HSI cameras. Consequently, the existing machine-learning-based approaches fail to learn to super-resolve HSIs for a wide variety of input-output band settings. We propose a single Meta-Learning-Based Super-Resolution (MLSR) model, which can take in HSI images at an arbitrary number of input bands’ peak wavelengths and generate SR HSIs with an arbitrary number of output bands’ peak wavelengths. We leverage NTIRE2020 and ICVL datasets to train and validate the performance of the MLSR model. The results show that the single proposed model can successfully generate super-resolved HSI bands at arbitrary input-output band settings. The results are better or at least comparable to baselines that are separately trained on a specific input-output band setting.