MC-ISTA-Net: Adaptive Measurement and Initialization and Channel Attention Optimization inspired Neural Network for Compressive Sensing
This work is incremental, aiming to enhance compressive sensing reconstruction for natural images by refining optimization-inspired neural networks.
The authors tackled the problem of improving compressive sensing reconstruction for natural images by addressing hand-crafted measurement matrices and initialization, as well as equal treatment of multi-channel features, resulting in a proposed neural network called MC-ISTA-Net.
The optimization inspired network can bridge convex optimization and neural networks in Compressive Sensing (CS) reconstruction of natural image, like ISTA-Net+, which mapping optimization algorithm: iterative shrinkage-thresholding algorithm (ISTA) into network. However, measurement matrix and input initialization are still hand-crafted, and multi-channel feature map contain information at different frequencies, which is treated equally across channels, hindering the ability of CS reconstruction in optimization-inspired networks. In order to solve the above problems, we proposed MC-ISTA-Net