Photonics Research, 2021, 9 (4): 0400B159, Published Online: Apr. 6, 2021
Intelligent coding metasurface holograms by physics-assisted unsupervised generative adversarial network
Figures & Tables
Fig. 1. (a) Sketch of our hologram system that consists of a 1 bit coding metasurface loading the hologram and a feed antenna. The distance between the holographic imaging plane and coding metasurface is 30 cm. (b) The meta-unit of the 1 bit coding metasurface. (c) The side-looking photograph of our hologram system. The interval between meta-units on the coding metasurface is 3.8 mm, and the feed antenna radiates the EM waves with frequencies from 34 GHz to 36 GHz.
Fig. 2. Schematic diagram of the proposed VAE-cWGAN. The generator together with the EM propagation process makes up the VAE structure. Two kinds of distance criteria (MSE and Wasserstein distance) are used to improve the imaging quality of the generator.
Fig. 3. (a) Three discrete-sequence sets sampled from distributions P 1 P 2 P 3 3 (b)] output by a generator trained only using the MSE loss. (d) The generated holographic image output by a generator trained using MSE loss and Wasserstein distance simultaneously.
Fig. 4. Generated holographic images at each training time corresponding to the valid target holographic images. One time of training is when training generator has three iterations after the training discriminator has one iteration.
Fig. 5. Testing results of our proposed intelligent metasurface hologram system. The target holographic images are randomly chosen from the testing MNIST dataset or images of handwritten letters. The simulation holographic images are calculated by Eq. (7 ) with the binarized current vectors J φ J φ
Fig. 6. Comparison results between the VAE-cGAN and GS algorithms. The top half presents the simulated results of the generated holographic images radiated by metasurface holograms designed by our VAE-cGAN and GS algorithms, respectively. Here, GS1, GS2, and GS3 are the generated holographic images obtained by running the GS algorithm three times in sequence. The values of MSE and PSNR evaluations are marked below the corresponding holographic images. The bottom half of this figure illustrates the statistical frequency histograms of the holographic image quality in terms of MSE and PSNR.
Che Liu, Wen Ming Yu, Qian Ma, Lianlin Li, Tie Jun Cui. Intelligent coding metasurface holograms by physics-assisted unsupervised generative adversarial network[J]. Photonics Research, 2021, 9(4): 0400B159.
PDF全文
