LADMM-Net: An Unrolled Deep Network For Spectral Image Fusion From Compressive Data
Hyperspectral (HS) and multispectral (MS) image fusion aims at estimating a high-resolution spectral image from a low-spatial-resolution HS image and a low-spectral-resolution MS image. Compressive spectral imaging (CSI) has emerged as an acquisition framework that captures the relevant information of spectral images using a reduced number of snapshots. Various spectral image fusion methods from multi-sensor CSI measurements have been proposed. Nevertheless, these methods exhibit high running times and face the drawback of choosing a representation transform. In this work, a deep learning architecture under the algorithm unrolling approach is proposed for solving the fusion problem from HS and MS compressive measurements. This architecture, dubbed LADMM-Net, casts each iteration of a linearized version of the alternating direction method of multipliers into a processing layer whose concatenation forms a deep network. The linearized approach leads to estimate the target variable without resorting to expensive matrix operations. This approach also estimates the image high-frequency component included in both the auxiliary variable and the Lagrange multiplier. The performance of the proposed technique is evaluated on two spectral image databases and one dataset captured at the laboratory. Extensive simulations show that the proposed method outperforms the state-of-the-art approaches that fuse spectral images from compressive data.
READ FULL TEXT