Accurate Spectral Super-Resolution from Single RGB Image Using Multi-scale CNN
Different from traditional hyperspectral super-resolution approaches that focus on improving the spatial resolution, spectral superresolution aims at producing a high-resolution hyperspectral image from the RGB observation with super-resolution in spectral domain. However, it is challenging to accurately reconstruct a high-dimensional continuous spectrum from three discrete intensity values at each pixel, since too much information is lost during the procedure where the latent hyperspectral image is downsampled (e.g., with ×10 scaling factor) in spectral domain to produce an RGB observation. To address this problem, we present a multi-scale deep convolutional neural network (CNN) to explicitly map the input RGB image into a hyperspectral image. Through symmetrically downsampling and upsampling the intermediate feature maps in a cascading paradigm, the local and non-local image information can be jointly encoded for spectral representation, ultimately improving the spectral reconstruction accuracy. Extensive experiments on a large hyperspectral dataset demonstrate the effectiveness of the proposed method.
Hyperspectral imaging Spectral super-resolution Multi-scale analysis Convolutional neural networks
Yiqi Yan Lei Zhang Jun Li Wei Wei Yanning Zhang
School of Electronics and Information,Northwestern Polytechnical University,Xian,China School of Computer Science,Northwestern Polytechnical University,Xian,China Guangdong Provincial Key Laboratory of Urbanization and Geo-simulation,School of Geography and Plann School of Computer Science,Northwestern Polytechnical University,Xian,China;National Engineering La
国际会议
广州
英文
206-217
2018-11-23（万方平台首次上网日期，不代表论文的发表时间）