Physicsdriven Selfsupervised Learning For Fast Highresolution Robust 3d Reconstruction Of Lightfield Microscopy Zhi Lu Manchang Jin Shuai Chen Xiaoge Wang Feihao Sun Qi Zhang Zhifeng Zhao Jiamin Wu Jingyu Yang Qionghai Dai by Zhi Lu & Manchang Jin & Shuai Chen & Xiaoge Wang & Feihao Sun & Qi Zhang & Zhifeng Zhao & Jiamin Wu & Jingyu Yang & Qionghai Dai instant download after payment.

Light-feld microscopy (LFM) and its variants have signifcantly advanced intravital high-speed 3D imaging. However, their practical applications remain limited due to trade-ofs among processing speed, fdelity, and generalization in existing reconstruction methods. Here we propose a physics-driven selfsupervised reconstruction network (SeReNet) for unscanned LFM and scanning LFM (sLFM) to achieve near-difraction-limited resolution at millisecondlevel processing speed. SeReNet leverages 4D information priors to not only achieve better generalization than existing deep-learning methods, especially under challenging conditions such as strong noise, optical aberration, and sample motion, but also improve processing speed by 700 times over iterative tomography. Axial performance can be further enhanced via fne-tuning as an optional add-on with compromised generalization. We demonstrate these advantages by imaging living cells, zebrafsh embryos and larvae, Caenorhabditiselegans, and mice. Equipped with SeReNet, sLFM now enables continuous day-long high-speed 3D subcellular imaging with over 300,000 volumes of large-scale intercellular dynamics, such as immune responses and neural activities, leading to widespread practical biological applications.