Phase reconstruction of inline holograms and three-dimensional topography visualization based on all-optical residual diffraction neural network

Electronic computer based neural network can recover high-resolution quantitative phase image from inline hologram to reveal the fine structure of sample, which may face issues such as intensive computing, energy-consumption and time-delay. In contrast, optical diffraction computing not only has super-fast parallel processing capabilities and extremely low energy consumption, but also is naturally compatible with the physical process of holographic imaging. However, since existing optical diffraction computing models is not able to preserve the phase detail in phase reconstruction, it just focuses on intensity recovery of holograms. To address this problem, this paper proposes an all-optical residual diffraction neural network (RDNN) architecture to obtain high-precision phase distribution of inline holograms. In this method, residual optical structures and cascaded diffraction layers designs are combined to effectively reduce the loss of phase information during reconstruction, thereby ensuring a high degree of consistency between the reconstructed phase and the original phase. A series of numerical simulation results show that the proposed architecture can be generalized to the phase reconstruction task of three-dimensional (3D) biological samples. In phase reconstruction of human erythrocytes, the average SSIM and PSNR reach 0.82 and 28, respectively. In addition, we assess the network’s performance with noisy holograms, demonstrating that, unlike fully connected diffraction neural network, this approach significantly enhances phase reconstruction quality, even under random gaussian noise These results indicates that the proposed RDNN is potential to replace the electronic neural network to achieve accurate phase reconstruction of inline holograms and provide an efficient solution to observe the living cell dynamics.