Spatial redundancy transformer for self-supervised fluorescence image denoising
Xinyang Li, Xiaowan Hu, Xingye Chen, Jiaqi Fan, Zhifeng Zhao, Jiamin Wu, Haoqian Wang, Qionghai Dai · 2023
Read Spatial redundancy transformer for self-supervised fluorescence image denoising by Xinyang Li, Xiaowan Hu, Xingye Chen, Jiaqi Fan, Zhifeng Zhao, Jiamin Wu, Haoqian Wang, Qionghai Dai (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10766531.txt.
Description
Xinyang Li and co-authors present a 2023 paper on cleaning noise from fluorescence microscope images without any clean examples to learn from. Fluorescence pictures are grainy by nature, and the noise hides fine biology. Their method, SRDTrans, exploits the fact that nearby pixels in an image repeat much of the same signal.
A sampling trick pulls paired patches from neighboring spots to train on, removing the need for fast repeat imaging. A light transformer design then reads both space and time patterns at low cost. The cleaned images kept fine detail without the waxy smoothing that plagues denoisers. Tests on single-molecule tracking and two-photon brain imaging reached top scores. The method assumes nothing about the sample, so it ports to many imaging styles.
Catalog record
| CREATOR | Xinyang Li, Xiaowan Hu, Xingye Chen, Jiaqi Fan, Zhifeng Zhao, Jiamin Wu, Haoqian Wang, Qionghai Dai |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 58 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |