Snapshot Interferometric 3D Imaging by Compressive Sensing and Deep Learning

2020/04/03 by Mu Qiao, Yangyang Sun, Qiao, Mu +9
Engineering · #Artificial intelligence #Compressed sensing #Computer science #Computer vision #Data cube #FOS: Electrical engineering #Frame rate #Hyperspectral imaging #Image and Video Processing (eess.IV) #Interferometry #Iterative reconstruction #Optical Coherence Tomography Applications #Optics #Photoacoustic and Ultrasonic Imaging #Physics #Single shot #Snapshot (computer storage) #Sparse and Compressive Sensing Techniques #Undersampling #Voxel #eess.IV #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2004.02633

16 pages, 12 figures

arxiv created 2020/04/03 · openalex publication_date 2020/04/03 · arxiv updated 2020/04/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

We demonstrate single-shot compressive three-dimensional (3D) (x, y, z) imaging based on interference coding. The depth dimension of the object is encoded into the interferometric spectra of the light field, resulting a (x, y, λ) datacube which is subsequently measured by a single-shot spectrometer. By implementing a compression ratio up to 400, we are able to reconstruct 1G voxels from a 2D measurement. Both an optimization based compressive sensing algorithm and a deep learning network are developed for 3D reconstruction from a single 2D coded measurement. Due to the fast acquisition speed, our approach is able to capture volumetric activities at native camera frame rates, enabling 4D (volumetric-temporal) visualization of dynamic scenes.

Citations

• Lattice light-sheet microscopy: Imaging molecules to embryos at high spatiotemporal resolution
• Two-Photon Laser Scanning Fluorescence Microscopy
• Nonlinear total variation based noise removal algorithms
• Subdiffraction Multicolor Imaging of the Nuclear Periphery with 3D Structured Illumination Microscopy
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Models

Related

• Learning Radiance Fields from a Single Snapshot Compressive Image
• Ensemble learning priors unfolding for scalable Snapshot Compressive Sensing
• Spatio-temporal Compressed Sensing with Coded Apertures and Keyed\n Exposures
• A Simple and Efficient Reconstruction Backbone for Snapshot Compressive Imaging
• Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms