Hyperspectral Image Denoising Employing a Spatial-Spectral Deep Residual Convolutional Neural Network
This work addresses noise reduction in hyperspectral images to improve interpretation for remote sensing applications, representing an incremental advance in deep learning methods for this domain.
The paper tackled hyperspectral image denoising by proposing a spatial-spectral deep residual convolutional neural network (HSID-CNN) that learns an end-to-end mapping from noisy to clean images, and it outperformed mainstream methods in quantitative metrics, visual quality, and classification accuracy.
Hyperspectral image (HSI) denoising is a crucial preprocessing procedure to improve the performance of the subsequent HSI interpretation and applications. In this paper, a novel deep learning-based method for this task is proposed, by learning a non-linear end-to-end mapping between the noisy and clean HSIs with a combined spatial-spectral deep convolutional neural network (HSID-CNN). Both the spatial and spectral information are simultaneously assigned to the proposed network. In addition, multi-scale feature extraction and multi-level feature representation are respectively employed to capture both the multi-scale spatial-spectral feature and fuse the feature representations with different levels for the final restoration. The simulated and real-data experiments demonstrate that the proposed HSID-CNN outperforms many of the mainstream methods in both the quantitative evaluation indexes, visual effects, and HSI classification accuracy.