Fourier-inspired neural module for real-time and high-fidelity computer-generated holography
Introduction
Learning-based computer-generated holography (CGH) algorithms appear as novel alternatives to generate phase-only holograms. However, most existing learning-based approaches underperform their iterative peers regarding display quality. Here, we recognize that current CNNs have difficulty learning cross-domain task due to the limited receptive field. In order to overcome this limitation, we propose a Fourier-inspired neural module, which can be easily integrated into various CGH frameworks and significantly enhance the quality of reconstructed images. By explicitly leveraging Fourier transforms within the neural network architecture, the mesoscopic information within the phase-only hologram could be more handily extracted. Both simulation and experiment were performed to showcase its capability. By incorporating it into U-Net and HoloNet, the PSNR of reconstructed images is measured at 29.16 dB and 33.50 dB during the simulation, which is 4.97 dB and 1.52 dB higher than those by the baseline U-Net and HoloNet, respectively. Similar trends are observed in the experimental results. We also experimentally demonstrated that the U-Net and HoloNet with the proposed module can generate a monochromatic 1080p hologram in 0.015 s and 0.020 s, respectively.
Numerical reconstruction
Experimental reconstruction
For more results, please refer to our [paper] and [codes].
Contact
If you have any questions, please contact d_zhenxing@sjtu.edu.cn.