OAM-basis underwater single-pixel imaging based on deep learning at a low sampling rate.

Our study introduces a pioneering underwater single-pixel imaging approach that employs an orbital angular momentum (OAM) basis as a sampling scheme and a dual-attention residual U-Net generative adversarial network (DARU-GAN) as reconstruction algorithm. This method is designed to address the challenges of low sampling rates and high turbidity typically encountered in underwater environments. The integration of the OAM-basis sampling scheme and the improved reconstruction network not only enhances reconstruction quality but also ensures robust generalization capabilities, effectively restoring underwater target images even under the stringent conditions of a 3.125% sampling rate and 128 NTU turbidity. The integration of OAM beams' inherent turbulence resistance with DARU-GAN's advanced image reconstruction capabilities makes it an ideal solution for high-turbid underwater imaging applications.