Masked autoencoder for highly compressed single-pixel imaging
- 14 August 2023
- journal article
- research article
- Published by Optica Publishing Group in Optics Letters
- Vol. 48 (16) , 4392-4395
Abstract
The single-pixel imaging technique uses multiple patterns to modulate the entire scene and then reconstructs a two-dimensional (2-D) image from the single-pixel measurements. Inspired by the statistical redundancy of natural images that distinct regions of an image contain similar information, we report a highly compressed single-pixel imaging technique with a decreased sampling ratio. This technique superimposes an occluded mask onto modulation patterns, realizing that only the unmasked region of the scene is modulated and acquired. In this way, we can effectively decrease 75% modulation patterns experimentally. To reconstruct the entire image, we designed a highly sparse input and extrapolation network consisting of two modules: the first module reconstructs the unmasked region from one-dimensional (1-D) measurements, and the second module recovers the entire scene image by extrapolation from the neighboring unmasked region. Simulation and experimental results validate that sampling 25% of the region is enough to reconstruct the whole scene. Our technique exhibits significant improvements in peak signal-to-noise ratio (PSNR) of 1.5 dB and structural similarity index measure (SSIM) of 0.2 when compared with conventional methods at the same sampling ratios. The proposed technique can be widely applied in various resource-limited platforms and occluded scene imaging.Keywords
Funding Information
- National Natural Science Foundation of China (61971045, 61991451, 62131003)
This publication has 17 references indexed in Scilit:
- Image-free single-pixel segmentationOptics & Laser Technology, 2022
- Imaging biological tissue with high-throughput single-pixel compressive holographyNature Communications, 2021
- High imaging quality of Fourier single pixel imaging based on generative adversarial networks at low sampling rateOptics and Lasers in Engineering, 2021
- Single-pixel compressive optical image hiding based on conditional generative adversarial networkOptics Express, 2020
- Deep learning for real-time single-pixel videoScientific Reports, 2018
- A Russian Dolls ordering of the Hadamard basis for compressive single-pixel imagingScientific Reports, 2017
- Multiple-image encryption scheme with a single-pixel detectorJournal of Modern Optics, 2016
- An efficient augmented Lagrangian method with applications to total variation minimizationComputational Optimization and Applications, 2013
- 3D Computational Imaging with Single-Pixel DetectorsScience, 2013
- Computational ghost imaging for remote sensingJournal of the Optical Society of America A, 2012