Saved in:
Bibliographic Details
Main Authors: Dai, Gaole, Tseng, Cheng-Ching, Wuwu, Qingpo, Zhang, Rongyu, Wang, Shaokang, Lu, Ming, Huang, Tiejun, Zhou, Yu, Tuz, Ali Ata, Gunzer, Matthias, Chen, Jianxu, Zhang, Shanghang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.19012
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911892227751936
author Dai, Gaole
Tseng, Cheng-Ching
Wuwu, Qingpo
Zhang, Rongyu
Wang, Shaokang
Lu, Ming
Huang, Tiejun
Zhou, Yu
Tuz, Ali Ata
Gunzer, Matthias
Chen, Jianxu
Zhang, Shanghang
author_facet Dai, Gaole
Tseng, Cheng-Ching
Wuwu, Qingpo
Zhang, Rongyu
Wang, Shaokang
Lu, Ming
Huang, Tiejun
Zhou, Yu
Tuz, Ali Ata
Gunzer, Matthias
Chen, Jianxu
Zhang, Shanghang
contents The rapid pace of innovation in biological microscopy imaging has led to large images, putting pressure on data storage and impeding efficient sharing, management, and visualization. This necessitates the development of efficient compression solutions. Traditional CODEC methods struggle to adapt to the diverse bioimaging data and often suffer from sub-optimal compression. In this study, we propose an adaptive compression workflow based on Implicit Neural Representation (INR). This approach permits application-specific compression objectives, capable of compressing images of any shape and arbitrary pixel-wise decompression. We demonstrated on a wide range of microscopy images from real applications that our workflow not only achieved high, controllable compression ratios (e.g., 512x) but also preserved detailed information critical for downstream analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2405_19012
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Implicit Neural Image Field for Biological Microscopy Image Compression
Dai, Gaole
Tseng, Cheng-Ching
Wuwu, Qingpo
Zhang, Rongyu
Wang, Shaokang
Lu, Ming
Huang, Tiejun
Zhou, Yu
Tuz, Ali Ata
Gunzer, Matthias
Chen, Jianxu
Zhang, Shanghang
Artificial Intelligence
The rapid pace of innovation in biological microscopy imaging has led to large images, putting pressure on data storage and impeding efficient sharing, management, and visualization. This necessitates the development of efficient compression solutions. Traditional CODEC methods struggle to adapt to the diverse bioimaging data and often suffer from sub-optimal compression. In this study, we propose an adaptive compression workflow based on Implicit Neural Representation (INR). This approach permits application-specific compression objectives, capable of compressing images of any shape and arbitrary pixel-wise decompression. We demonstrated on a wide range of microscopy images from real applications that our workflow not only achieved high, controllable compression ratios (e.g., 512x) but also preserved detailed information critical for downstream analysis.
title Implicit Neural Image Field for Biological Microscopy Image Compression
topic Artificial Intelligence
url https://arxiv.org/abs/2405.19012