FM2S: Towards Spatially-Correlated Noise Modeling in Zero-Shot Fluorescence Microscopy Image Denoising

TL;DR

FM2S introduces a zero-shot fluorescence microscopy denoising method that models spatially-correlated noise effectively, outperforming existing approaches with minimal parameters and rapid training, suitable for diverse biomedical imaging scenarios.

Contribution

The paper presents FM2S, a novel zero-shot denoiser with adaptive noise synthesis, a two-stage learning strategy, and an ultra-lightweight network, addressing real FMI noise challenges.

Findings

Outperforms CVF-SID by 1.4dB PSNR on average.

Requires only 0.1% parameters of state-of-the-art models.

Maintains stable performance across different noise levels.

Abstract

Fluorescence microscopy image (FMI) denoising faces critical challenges due to the compound mixed Poisson-Gaussian noise with strong spatial correlation and the impracticality of acquiring paired noisy/clean data in dynamic biomedical scenarios. While supervised methods trained on synthetic noise (e.g., Gaussian/Poisson) suffer from out-of-distribution generalization issues, existing self-supervised approaches degrade under real FMI noise due to oversimplified noise assumptions and computationally intensive deep architectures. In this paper, we propose Fluorescence Micrograph to Self (FM2S), a zero-shot denoiser that achieves efficient FMI denoising through three key innovations: 1) A noise injection module that ensures training data sufficiency through adaptive Poisson-Gaussian synthesis while preserving spatial correlation and global statistics of FMI noise for robust model generalization; 2) A two-stage progressive learning strategy that first recovers structural priors via pre-denoised targets then refines high-frequency details through noise distribution alignment; 3) An ultra-lightweight network (3.5k parameters) enabling rapid convergence with 270$\times$ faster training and inference than SOTAs. Extensive experiments across FMI datasets demonstrate FM2S's superiority: It outperforms CVF-SID by 1.4dB PSNR on average while requiring 0.1% parameters of AP-BSN. Notably, FM2S maintains stable performance across varying noise levels, proving its practicality for microscopy platforms with diverse sensor characteristics. Code and datasets will be released.