Super-coding resolution single-pixel imaging based on unpaired data-driven deep learning

•A super-coding resolution single-pixel imaging method based on unpaired data-driven deep learning is proposed.•With the help of the Cycle-gan network, paired label datasets are not required. It reduces the pressure of the dataset.•Low-quality preliminary results with low pixel resolution are preferentially obtained. It can reconstruct images with high-quality and high pixel resolution at low sampling rates.