Deep Learning of Compressed Sensing Operators with Structural Similarity Loss
This work addresses compressed sensing for signal processing applications, offering a novel loss function that may enhance reconstruction accuracy, though it appears incremental as it builds on existing deep learning frameworks.
The authors tackled the problem of compressed sensing reconstruction by proposing an end-to-end deep learning approach that jointly optimizes sensing and reconstruction using a Structural Similarity (SSIM) loss instead of Mean Squared Error (MSE). They compared their method with state-of-the-art techniques in terms of SSIM and MSE scores, showing improved reconstruction quality.
Compressed sensing (CS) is a signal processing framework for efficiently reconstructing a signal from a small number of measurements, obtained by linear projections of the signal. In this paper we present an end-to-end deep learning approach for CS, in which a fully-connected network performs both the linear sensing and non-linear reconstruction stages. During the training phase, the sensing matrix and the non-linear reconstruction operator are jointly optimized using Structural similarity index (SSIM) as loss rather than the standard Mean Squared Error (MSE) loss. We compare the proposed approach with state-of-the-art in terms of reconstruction quality under both losses, i.e. SSIM score and MSE score.