Convolutional Neural Networks for Non-iterative Reconstruction of Compressively Sensed Images
This work addresses the challenge of real-time image reconstruction in compressive sensing for applications like imaging and object tracking, though it is incremental as it builds on existing deep learning methods.
The authors tackled the problem of computationally expensive and ineffective compressive sensing image reconstruction at low measurement rates by proposing ReconNet, a deep neural network that maps compressive measurements to image blocks in a non-iterative manner, achieving higher PSNRs compared to iterative algorithms and enabling real-time reconstruction.
Traditional algorithms for compressive sensing recovery are computationally expensive and are ineffective at low measurement rates. In this work, we propose a data driven non-iterative algorithm to overcome the shortcomings of earlier iterative algorithms. Our solution, ReconNet, is a deep neural network, whose parameters are learned end-to-end to map block-wise compressive measurements of the scene to the desired image blocks. Reconstruction of an image becomes a simple forward pass through the network and can be done in real-time. We show empirically that our algorithm yields reconstructions with higher PSNRs compared to iterative algorithms at low measurement rates and in presence of measurement noise. We also propose a variant of ReconNet which uses adversarial loss in order to further improve reconstruction quality. We discuss how adding a fully connected layer to the existing ReconNet architecture allows for jointly learning the measurement matrix and the reconstruction algorithm in a single network. Experiments on real data obtained from a block compressive imager show that our networks are robust to unseen sensor noise. Finally, through an experiment in object tracking, we show that even at very low measurement rates, reconstructions using our algorithm possess rich semantic content that can be used for high level inference.