Holographic image denoising for dense droplet field using conditional diffusion model.

The Letter delves into an approach to holographic image denoising, drawing inspiration from the generative paradigm. It introduces a conditional diffusion model framework that effectively suppresses twin-image noises and speckle noises in dense particle fields with a large depth of field (DOF). Specific training and inference configurations are meticulously outlined. For evaluation, the method is tested using calibration dot board data and droplet field data, encompassing gel atomization captured via inline holography and aviation kerosene swirl spray through off-axis holography. The performance is assessed using three distinct metrics. The metric outcomes, along with representative examples, robustly demonstrate its superior noise reduction, detail preservation, and generalization capabilities when compared to two other methods. The proposed method not only pioneers the field of generative holographic image denoising but also highlights its potential for industrial applications, given its reduced dependency on high-quality training labels.