High-speed computer-generated holography using an autoencoder-based deep neural network

Wu, Juanjuan; Liu, Ke-Xuan; Sui, Xiaomeng; Cao, Liangcai

doi:10.1364/ol.425485

Cited by 129 publications

(54 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The training results of the proposed method are compared with holograms generated by other methods [24,30].…”

Section: Experiments and Results Analysismentioning

confidence: 99%

“…The computational holograms based on the iterative ASM are shown in Figure 4d and the numerical reconstruction results are shown in Figure 4e. We also use recent method named holo-encoder [24] to generate and reconstruct the same image and compare the image quality with our work, shown in Figure 4f,g.…”

Section: Single Planar Numerical Reconstructionmentioning

confidence: 99%

“…For the image size of 512 × 512 pixels, the calculating times of the deep learning-based method and the iterative ASM for calculating a single hologram with a computer with an Intel Core i9-10980XE processor, a clock frequency of 3.0 GHz and a memory size of 32 GB are shown in Table 1. The time consuming for calculating holograms is shorter in the proposed network method, which is about 50 times faster than the iterative ASM at the same quality level; here, we do not consider that the training time of the network is about 50 h. We compare with a recent related study (called as holo-encoder) [24] and calculate the PSNR and RMSE of reconstructed images from the phase hologram generated using a holo-encoder method. The PSNR is 23.3611 and RMSE is 0.0548.…”

Section: Single Planar Numerical Reconstructionmentioning

confidence: 99%

“…Therefore, it is an excellent choice for fast and efficient processing of optical information (including fast CGH generation). Neural networks have also been successfully applied to digital holography [16], computational imaging [17][18][19], hologram generation [20][21][22][23][24], etc.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Computing 3D Phase-Type Holograms Based on Deep Learning Method

Zheng

Zhou

et al. 2021

Photonics

View full text Add to dashboard Cite

Computer holography is a technology that use a mathematical model of optical holography to generate digital holograms. It has wide and promising applications in various areas, especially holographic display. However, traditional computational algorithms for generation of phase-type holograms based on iterative optimization have a built-in tradeoff between the calculating speed and accuracy, which severely limits the performance of computational holograms in advanced applications. Recently, several deep learning based computational methods for generating holograms have gained more and more attention. In this paper, a convolutional neural network for generation of multi-plane holograms and its training strategy is proposed using a multi-plane iterative angular spectrum algorithm (ASM). The well-trained network indicates an excellent ability to generate phase-only holograms for multi-plane input images and to reconstruct correct images in the corresponding depth plane. Numerical simulations and optical reconstructions show that the accuracy of this method is almost the same with traditional iterative methods but the computational time decreases dramatically. The result images show a high quality through analysis of the image performance indicators, e.g., peak signal-to-noise ratio (PSNR), structural similarity (SSIM) and contrast ratio. Finally, the effectiveness of the proposed method is verified through experimental investigations.

show abstract

“…The training results of the proposed method are compared with holograms generated by other methods [24,30].…”

Section: Experiments and Results Analysismentioning

confidence: 99%

Section: Single Planar Numerical Reconstructionmentioning

confidence: 99%

Section: Single Planar Numerical Reconstructionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Computing 3D Phase-Type Holograms Based on Deep Learning Method

Zheng

Zhou

et al. 2021

Photonics

View full text Add to dashboard Cite

show abstract

“…The total calculation time is 1298.67 ms, which limits the application of the proposed approach in dynamic 3D display. Considering that both the calculation of CGDMs and the generation of CGHs can be realized by deep learning [43], further optimization of the calculation time would be practical. Combining the proposed method with deep learning network is the future direction of the work.…”

Section: Discussionmentioning

confidence: 99%

Holographic 3D Display Using Depth Maps Generated by 2D-to-3D Rendering Approach

Sui

Cao

2021

Applied Sciences

Self Cite

View full text Add to dashboard Cite

Holographic display has the potential to be utilized in many 3D application scenarios because it provides all the depth cues that human eyes can perceive. However, the shortage of 3D content has limited the application of holographic 3D displays. To enrich 3D content for holographic display, a 2D to 3D rendering approach is presented. In this method, 2D images are firstly classified into three categories, including distant view images, perspective view images and close-up images. For each category, the computer-generated depth map (CGDM) is calculated using a corresponding gradient model. The resulting CGDMs are applied in a layer-based holographic algorithm to obtain computer-generated holograms (CGHs). The correctly reconstructed region of the image changes with the reconstruction distance, providing a natural 3D display effect. The realistic 3D effect makes the proposed approach can be applied in many applications, such as education, navigation, and health sciences in the future.

show abstract

In‐Situ Wavefront Correction via Physics‐Informed Neural Network

Long,

Gao,

Yuan

et al. 2024

Laser & Photonics Reviews

View full text Add to dashboard Cite

Wavefront distortions pose a significant limitation in various optical applications, hindering further advancements in optical system performance. In this study, a novel generic calibration model based on Zernike‐fitting neural network (ZFNN) is proposed, which enables insitu wavefront correction with just a single‐shot measurement. The experimental setup follows a standard or equivalent focal‐field imaging optical path, allowing calibration without the need to remove any components from the optical system. The ZFNN, a physics‐informed neural network, offers the advantage of not requiring prior training, eliminating the need for extensive labeled data. With a fully connected network architecture and a modest number of neurons (469), the ZFNN achieves exceptionally fast optimization speed and meets the basic requirements for real‐time calibration. Consequently, this approach holds great potential for applications such as rapid calibration of optical systems, high‐precision light field modulation, and various advanced imaging techniques.

show abstract

High-speed computer-generated holography using an autoencoder-based deep neural network

Cited by 129 publications

References 22 publications

Computing 3D Phase-Type Holograms Based on Deep Learning Method

Computing 3D Phase-Type Holograms Based on Deep Learning Method

Holographic 3D Display Using Depth Maps Generated by 2D-to-3D Rendering Approach

In‐Situ Wavefront Correction via Physics‐Informed Neural Network

Contact Info

Product

Resources

About