.png){kind=icon}
.png){kind=icon}
Return
Single-pixel imaging based on self-supervised conditional mask classifier-free guidance
.png){kind=icon}
OA
AI
DOI：10.1364/OE.518455.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Reconstructing high -quality images at a low measurement rate is a pivotal objective of Single -Pixel Imaging (SPI). Currently, deep learning methods achieve this by optimizing the loss between the target image and the original image, thereby constraining the potential of low measurement values. We employ conditional probability to ameliorate this, introducing the classifier -free guidance model (CFG) for enhanced reconstruction. We propose a self -supervised conditional masked classifier -free guidance (SCM-CFG) for single -pixel reconstruction. At a 10% measurement rate, SCM-CFG efficiently completed the training task, achieving an average peak signal-to-noise ratio (PSNR) of 26.17 dB on the MNIST dataset. This surpasses other methods of photon imaging and computational ghost imaging. It demonstrates remarkable generalization performance. Moreover, thanks to the outstanding design of the conditional mask in this paper, it can significantly enhance the accuracy of reconstructed images through overlay. SCM-CFG achieved a notable improvement of an average of 7.3 dB in overlay processing, in contrast to only a 1 dB improvement in computational ghost imaging. Subsequent physical experiments validated the effectiveness of SCM-CFG. (c) 2024 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement