Learning-based high-quality image recovery from 1D signals obtained by single-pixel imaging

As an innovative and computational imaging technique, it is critical for single-pixel imaging (SPI) to achieve a high reconstruction quality. However, the reconstruction image quality in conventional SPI is heavily dependent on the sampling rate. In this work, we present a learning-based SPI approach for high-quality image reconstruction under a low sampling rate. A bucket detector included in our optical setup is used to collect the one-dimensional (1D) signals reflected from a two-dimensional (2D) object and an end-to-end generative adversarial network (EGAN) which is pre-trained with simulated data is utilized to implement the reconstruction of the object. The results show that the proposed approach is able to produce high quality approximations of 2D images from optically collected 1D bucket signals at a very low sampling ratio. It can also be shown a better performance can be achieved by compared with previous studies on the same dataset, such as conventional SPI, compressive-sensing ghost imaging (CSGI) and U-net-based SPI approaches. • A learning-based single-pixel imaging (SPI) for high-quality image reconstruction under a very low sampling rate is proposed. • The implementation of efficient image reconstruction is performed by an end-to-end generative adversarial network. • The performance of the proposed SPI is demonstrated under different sampling rate conditions using both simulated and optical experiments. • Compared with other techniques, the pre-trained EGAN can output higher quality approximations of object images.