Vision transformer-based, high-fidelity, computer-generated holography

Zhenxing Dong; Chao Xu; Yaoqi Tang; Yuye Ling; Yan Li; Yikai Su

doi:10.1117/12.2648987

14 March 2023 Vision transformer-based, high-fidelity, computer-generated holography

Zhenxing Dong, Chao Xu, Yaoqi Tang, Yuye Ling, Yan Li, Yikai Su

Proceedings Volume 12443, Advances in Display Technologies XIII; 1244307 (2023) https://doi.org/10.1117/12.2648987
Event: SPIE OPTO, 2023, San Francisco, California, United States

Abstract

Current learning-based Computer-Generated Holography (CGH) algorithms often utilize Convolutional Neural Networks (CNN)-based architectures. However, the CNN-based non-iterative methods mostly underperform the State-Of-The-Art (SOTA) iterative algorithms such as Stochastic Gradient Descent (SGD) in terms of display quality. Inspired by the global attention mechanism of Vision Transformer (ViT), we propose a novel unsupervised autoencoder-based ViT for generating phase-only holograms. Specifically, for the encoding part, we use Uformer to generate the holograms. For the decoding part, we use the Angular Spectrum Method (ASM) instead of a learnable network to reconstruct the target images. To validate the effectiveness of the proposed method, numerical simulations and optical reconstructions are performed to compare our proposal against both iterative algorithms and CNN-based techniques. In the numerical simulations, the PSNR and SSIM of the proposed method are 26.78 dB and 0.832, which are 4.02 dB and 0.09 higher than that of the CNN-based method, respectively. Moreover, the proposed method contains less speckles and features a higher display quality than other CGH methods in experiments. We suggest the improvement might be ascribed to the ViT’s global attention mechanism, which is more suitable for learning the cross-domain mapping from image (spatial) domain to hologram (Fourier) domain. We believe the proposed ViT-based CGH algorithm could be a promising candidate for future real-time high-fidelity holographic displays.

Conference Presentation

Citation Download Citation

Zhenxing Dong, Chao Xu, Yaoqi Tang, Yuye Ling, Yan Li, and Yikai Su "Vision transformer-based, high-fidelity, computer-generated holography", Proc. SPIE 12443, Advances in Display Technologies XIII, 1244307 (14 March 2023); https://doi.org/10.1117/12.2648987

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available