M-Denoiser: Unsupervised image denoising for real-world optical and electron microscopy data

Xiaoya Chong, Min Cheng, Wenqi Fan, Qing Li, Howard Leung

Abstract: Highlights•Microscopy noise has a Poisson–Gaussian distribution and is ruled by Poisson noise.•A shatter for breaking dependency and unsupervised loss on paired images are proposed.•M-Denoiser improves the quality of microscopy data and helps with downstream tasks.