Deep Learning for Nonlinear Diffractive Imaging
share
Image reconstruction under multiple light scattering is crucial for a number of important applications in cell microscopy and tissue imaging. The reconstruction problem is often formulated as a nonconvex optimization, where a nonlinear measurement model is used to account for multiple scattering and a regularizer is used to enforce the prior on the object. In this letter, We propose a powerful alternative to this optimization-based view of image reconstruction by designing and training a deep convolutional neural network (CNN) for inverting multiple scattering. Simulations show that the proposed formulation is substantially faster and achieves higher imaging quality compared to the state-of-the-art methods based on optimization.
READ FULL TEXT
