logo
ResearchBunny Logo
Neural space-time model for dynamic multi-shot imaging

Biology

Neural space-time model for dynamic multi-shot imaging

R. Cao, N. S. Divekar, et al.

Discover how Ruiming Cao and colleagues have developed a groundbreaking neural space-time model (NSTM) that enhances computational imaging by jointly estimating scene dynamics and motion without prior data. This innovative approach minimizes motion artifacts and enables precise motion dynamics recovery, particularly in advanced microscopy techniques.

00:00
00:00
Playback language: English
Abstract
This paper introduces a neural space-time model (NSTM) for computational imaging reconstructions from multiple sequentially captured measurements. The model jointly estimates the scene and its motion dynamics without data priors or pre-training, mitigating motion artifacts and resolving sample dynamics from raw measurements. NSTM's efficacy is demonstrated in differential phase-contrast microscopy, 3D structured illumination microscopy, and rolling-shutter DiffuserCam, showcasing its ability to recover subcellular motion dynamics and reduce misinterpretations of living systems caused by motion artifacts.
Publisher
Nature Methods
Published On
Sep 24, 2024
Authors
Ruiming Cao, Nikita S. Divekar, James K. Nuñez, Srigokul Upadhyayula, Laura Waller
Tags
neural space-time model
computational imaging
motion dynamics
microscopy
motion artifacts
raw measurements
subcellular dynamics

Related Publications

Explore these studies to deepen your understanding of the subject.

Massively parallel electro-optic sampling of space-encoded optical pulses for ultrafast multi-dimensional imaging
Engineering and Technology

Massively parallel electro-optic sampling of space-encoded optical pulses for ultrafast multi-dimensional imaging

Y. Na, H. Kwak, et al.

Multi-state quantum simulations via model-space quantum imaginary time evolution
Physics

Multi-state quantum simulations via model-space quantum imaginary time evolution

T. Tsuchimochi, Y. Ryo, et al.

A deep convolutional neural network for real-time full profile analysis of big powder diffraction data
Chemistry

A deep convolutional neural network for real-time full profile analysis of big powder diffraction data

H. Dong, K. T. Butler, et al.

A deep unrolled neural network for real-time MRI-guided brain intervention
Medicine and Health

A deep unrolled neural network for real-time MRI-guided brain intervention

Z. He, Y. Zhu, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny