Generative adversarial network‐based single‐pixel imaging
Authors:
- 10 May 2022
- journal article
- research article
- Published by Wiley in Journal of the Society for Information Display
- Vol. 30 (8) , 648-656
Abstract
Single‐pixel imaging can reconstruct two‐dimensional images of a scene with only a single‐pixel detector. It has been widely used for imaging in nonvisible bandwidth (e.g., near‐infrared and X‐ray) where focal‐plane array sensors are challenging to be manufactured. In this paper, we propose a generative adversarial network‐based reconstruction algorithm for single‐pixel imaging, which demonstrates efficient reconstruction in high speed and higher reconstruction quality compared with other state‐of‐the‐art deep learning‐based reconstruction methods. We also co‐optimize sampling masks and reconstruction pipeline to enhance the performance. We verify the proposed method with both synthetic and real‐world experiments and demonstrate a good quality of reconstruction of a real‐world plaster using a 5% sampling rate.Keywords
All Related Versions
Funding Information
- Central University Basic Research Fund of China (3132018186)
- National Natural Science Foundation of China (61501077)
This publication has 23 references indexed in Scilit:
- From Denoising to Compressed SensingIEEE Transactions on Information Theory, 2016
- Deep learningNature, 2015
- Single-pixel infrared and visible microscopeOptica, 2014
- Terahertz compressive imaging with metamaterial spatial light modulatorsNature Photonics, 2014
- Compressive single-pixel snapshot x-ray diffraction imagingOptics Letters, 2013
- Computational ghost imagingPhysical Review A, 2008
- Compressive Sensing [Lecture Notes]IEEE Signal Processing Magazine, 2007
- Compressed sensingIEEE Transactions on Information Theory, 2006
- Stable signal recovery from incomplete and inaccurate measurementsCommunications on Pure and Applied Mathematics, 2006
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics2002