Work

Background2Background: a self-supervised background removal framework for high dimensional microscopy

Year: 2026

Type: preprint

Abstract: High-dimensional microscopy captures features across space, time, and spectrum, but complex backgrounds obscure signals. We present Background2Background (B2B), a self-supervised background removal framework leveraging the backgrounds larger correlation relative to the signal. Local pixel shuffling disrupts signal correlations while preserving background structure, transforming signals into effective noise for Noise2Noise-based background removal. Across fluorescence, stimulated Raman scattering and mid-infrared photothermal imaging, B2B achieves over 40-fold background suppression and reveals hidden signatures.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.17615

Authors: Ding, Guangrui, Lin, Haonan, Tang, Rong, Weinberg, Bethany, Ao, Jianpeng, Xia, Qing, Hu, Guorong, Sun, Dingcheng, Yin, Jiaze, Tian, Lei, Cheng, Ji-Xin

Institutions: Boston University, Georgia Institute of Technology, Emory University, The Wallace H. Coulter Department of Biomedical Engineering

Language: English

Topic: Image and Signal Denoising Methods

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Institutes of Health

OpenAlex ID: W7221836457

Cites: 15

Cited by:

Related to: 10