Poisson noise due to the quantization of light is a universal phenomenon, especially severe in low light imaging conditions. Such noise is unavoidable and impacts computational imaging systems and algorithms. In this paper, we show how to efficiently use deep neural networks to handle Poisson noise in the context of a phase retrieval problem. For sparse objects, we demonstrate successful phase recovery with as little as 10 photons per detector pixel per acquisition cycle.
© 2018 The Author(s)PDF Article