Log Focal Frequency Loss for Bioimage Restoration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Xingjian, Leclech, Claire, Blivet-Bailly, Louison, Barakat, Abdul I., Angelini, Elsa D.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914288759734272
author Zhang, Xingjian
Leclech, Claire
Blivet-Bailly, Louison
Barakat, Abdul I.
Angelini, Elsa D.
author_facet Zhang, Xingjian
Leclech, Claire
Blivet-Bailly, Louison
Barakat, Abdul I.
Angelini, Elsa D.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_20878
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Log Focal Frequency Loss for Bioimage Restoration
Zhang, Xingjian
Leclech, Claire
Blivet-Bailly, Louison
Barakat, Abdul I.
Angelini, Elsa D.
Quantitative Methods
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.
title Log Focal Frequency Loss for Bioimage Restoration
topic Quantitative Methods
url https://arxiv.org/abs/2601.20878