Log Focal Frequency Loss for Bioimage Restoration

TL;DR

This paper introduces a novel log focal frequency loss tailored for microscopy image restoration, effectively balancing frequency components to enhance structural and detail preservation in biological images.

Contribution

The paper proposes a new frequency loss function inspired by human visual perception, improving GAN-based microscopy image restoration by balancing spectral information.

Findings

Improved image quality metrics over existing methods.

Effective preservation of fine structures and edges.

Validated on microscopy deblurring and denoising tasks.

Abstract

Image restoration of biological structures in microscopy poses unique challenges for preserving fine textures and sharp edges. While recent GAN-based image restoration formulations have introduced frequency-domain losses for natural images, microscopy images pose distinct challenges with large dynamic ranges and sparse but critical structures with spatially-variable contrast. Inspired by the principle of logarithmic perception in human vision, we propose a log focal frequency loss (LFFL) tailored for microscopy restoration. This loss combines adaptive spectral weighting from log-space differences with log-dampened error measurement, ensuring balanced reconstruction across all frequency bands while preserving both structural coherence and fine details. We tested our GAN-based framework on two use-cases with real ground-truths: deblurring of fluorescence images of cell nuclei on microgroove substrates and denoising of zebrafish embryo images from the FMD dataset. Compared to training with only spatial-domain losses and with existing frequency-domain losses, our method achieves improvements across several quality metrics. Code is available at github.com/xjzhaang/log-focal-frequency-loss.