Overview of the ARSPI Framework (IMAGE)

Editorial Office of Opto-Electronic Journals Group

Overview of the ARSPI Framework

Caption

(a) Schematic diagram of the signal acquisition process in single-pixel imaging. (b) Downsampling operator: performs image downsampling according to the adjustable scaling factor α. (c) The proposed ARSPI algorithm. A fixed random noise tensor is used to generate the high-pixel-resolution image, which is then downsampled by the average pooling operator to obtain the measurement-pixel-resolution image. The simulated measurements are generated through the SPI physical model. The network parameters are updated via the loss function, and the image quality is iteratively optimized. (d) Reconstruction results together with the optimization dynamics.

Credit

Prof. Xiaoxi Chen from University of Electronic Science and Technology of China, China; Prof. Pinghe Wang from University of Electronic Science and Technology of China, China; Prof. Fake Lu from State University of New York, USA; Prof. Guohua Shi from Chinese Academy of Sciences, China. Image source link: https://www.oejournal.org/oea/article/doi/10.29026/oea.2026.260133

Usage Restrictions

Credit must be given to the creator.

License

CC BY

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.