Saved in:
Bibliographic Details
Main Authors: Sturm, Moritz, Cerrone, Lorenzo, Hamprecht, Fred A.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.16421
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929329761419264
author Sturm, Moritz
Cerrone, Lorenzo
Hamprecht, Fred A.
author_facet Sturm, Moritz
Cerrone, Lorenzo
Hamprecht, Fred A.
contents Cell tracking remains a pivotal yet challenging task in biomedical research. The full potential of deep learning for this purpose is often untapped due to the limited availability of comprehensive and varied training data sets. In this paper, we present SynCellFactory, a generative cell video augmentation. At the heart of SynCellFactory lies the ControlNet architecture, which has been fine-tuned to synthesize cell imagery with photorealistic accuracy in style and motion patterns. This technique enables the creation of synthetic yet realistic cell videos that mirror the complexity of authentic microscopy time-lapses. Our experiments demonstrate that SynCellFactory boosts the performance of well-established deep learning models for cell tracking, particularly when original training data is sparse.
format Preprint
id arxiv_https___arxiv_org_abs_2404_16421
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SynCellFactory: Generative Data Augmentation for Cell Tracking
Sturm, Moritz
Cerrone, Lorenzo
Hamprecht, Fred A.
Computer Vision and Pattern Recognition
Cell tracking remains a pivotal yet challenging task in biomedical research. The full potential of deep learning for this purpose is often untapped due to the limited availability of comprehensive and varied training data sets. In this paper, we present SynCellFactory, a generative cell video augmentation. At the heart of SynCellFactory lies the ControlNet architecture, which has been fine-tuned to synthesize cell imagery with photorealistic accuracy in style and motion patterns. This technique enables the creation of synthetic yet realistic cell videos that mirror the complexity of authentic microscopy time-lapses. Our experiments demonstrate that SynCellFactory boosts the performance of well-established deep learning models for cell tracking, particularly when original training data is sparse.
title SynCellFactory: Generative Data Augmentation for Cell Tracking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.16421