Complex-valued Retrievals From Noisy Images Using Diffusion Models
This addresses the challenge of improving image quality in optical microscopy for researchers, though it is incremental as it extends existing diffusion models to new noise types and data.
The study tackled the problem of restoring complex-valued images from noisy real-valued intensity measurements affected by Poisson noise, using a generalized diffusion model that achieved high-quality results in simulations and biological data.
In diverse microscopy modalities, sensors measure only real-valued intensities. Additionally, the sensor readouts are affected by Poissonian-distributed photon noise. Traditional restoration algorithms typically aim to minimize the mean squared error (MSE) between the original and recovered images. This often leads to blurry outcomes with poor perceptual quality. Recently, deep diffusion models (DDMs) have proven to be highly capable of sampling images from the a-posteriori probability of the sought variables, resulting in visually pleasing high-quality images. These models have mostly been suggested for real-valued images suffering from Gaussian noise. In this study, we generalize annealed Langevin Dynamics, a type of DDM, to tackle the fundamental challenges in optical imaging of complex-valued objects (and real images) affected by Poisson noise. We apply our algorithm to various optical scenarios, such as Fourier Ptychography, Phase Retrieval, and Poisson denoising. Our algorithm is evaluated on simulations and biological empirical data.