Experimental study demonstrates light-speed image processing via Fourier-space diffractive neural networks, indicating a path toward ultra-fast, low-power optical computer vision.
In this Letter we propose the Fourier-space diffractive deep neural network (F-D²NN) for all-optical image processing that performs advanced computer vision tasks at the speed of light. The F-D²NN is achieved by placing the extremely compact diffractive modulation layers at the Fourier plane or both Fourier and imaging planes of an optical system, where the optical nonlinearity is introduced from ferroelectric thin films. We demonstrated that F-D²NN can be trained with deep learning algorithms for all-optical saliency detection and high-accuracy object classification.
No takes yet. Share an insight, caveat, or question.
Yan et al. (2019) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: