Multi-depth hologram generation from two-dimensional images by deep learning

Ishii, Yoshiyuki; Wang, Fan; Shiomi, Harutaka; Kakue, Takashi; Ito, Tomoyoshi; Shimobaba, Tomoyoshi

doi:10.1016/j.optlaseng.2023.107758

Cited by 7 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[64,65] Furthermore, as a result of inadequate network architecture and improper handling of occlusion relationships, some deep learning-based methods yield subpar scene clarity and fall short of achieving accurate occlusion culling in the reconstructed scenes. [60,66] Here, we propose a forward-backward-diffraction framework for the first time to compute multi-depth diffraction fields and combine it with a carefully designed fully convolutional neural network (FCN) to generate multi-depth holograms, to the best of our knowledge. This framework implements occlusion of the foreground on the background's diffraction field during the forward propagation process of the diffraction field and determines the reconstruction distance through the backward propagation of the diffraction field.…”

Section: Introductionmentioning

confidence: 99%

Generating Multi‐Depth 3D Holograms Using a Fully Convolutional Neural Network

Yan,

Liu,

et al. 2024

Advanced Science

View full text Add to dashboard Cite

Efficiently generating 3D holograms is one of the most challenging research topics in the field of holography. This work introduces a method for generating multi‐depth phase‐only holograms using a fully convolutional neural network (FCN). The method primarily involves a forward–backward‐diffraction framework to compute multi‐depth diffraction fields, along with a layer‐by‐layer replacement method (L2RM) to handle occlusion relationships. The diffraction fields computed by the former are fed into the carefully designed FCN, which leverages its powerful non‐linear fitting capability to generate multi‐depth holograms of 3D scenes. The latter can smooth the boundaries of different layers in scene reconstruction by complementing information of occluded objects, thus enhancing the reconstruction quality of holograms. The proposed method can generate a multi‐depth 3D hologram with a PSNR of 31.8 dB in just 90 ms for a resolution of 2160 × 3840 on the NVIDIA Tesla A100 40G tensor core GPU. Additionally, numerical and experimental results indicate that the generated holograms accurately reconstruct clear 3D scenes with correct occlusion relationships and provide excellent depth focusing.

show abstract

Section: Introductionmentioning

confidence: 99%

Generating Multi‐Depth 3D Holograms Using a Fully Convolutional Neural Network

Yan,

Liu,

et al. 2024

Advanced Science

View full text Add to dashboard Cite

show abstract

“…Spatial unwrapping techniques such as minimum norm, quality guided methods etc have limitations in handling the phase discontinuities and disjoint regions whereas temporal techniques requires multi frames or multi frequency fringes [5]. Deep learning is gaining attraction in various fields such as microscopy, holography, super resolution imaging, optical image encryption, interferometry, natural language processing (NLP), facial recognition, autonomous vehicles, medical image analysis, drug discovery, disease diagnosis, treatment recommendation, etc [7][8][9][10][11]. Advent of newer and complex architectures because of the availability of necessary hardware such as Graphics Processing Units (GPUs) and Tensor Processing units (TPUs) has improved the performance of deep learning in various fields [12].…”

Section: Introductionmentioning

confidence: 99%

Transformer based deep learning hybrid architecture for phase unwrapping

Bujagouni,

Pradhan

2024

Phys. Scr.

View full text Add to dashboard Cite

A deep learning Hybrid architecture for phase unwrapping has been proposed. The hybrid architecture is based on integration of Convolutional Neural Networks (CNN) with Vision Transformer. The performance of Hybrid architecture/network in phase unwrapping is compared against CNN based standard UNET network. Structural Similarity Index (SSIM) and Root Mean Square Error (RMSE) have been used as performance metrics to assess the performance of these deep learning networks for phase unwrapping. To train and test the networks, dataset with high mean Entropy has been generated using Gaussian filtering of random noise in Fourier plane. The Hybrid architecture is tested on test dataset and is found to have superior performance metrics against the UNET network. Their performance is also tested in noisy environment with various noise levels and Hybrid architecture demonstrated better anti-noise capability than UNET network. Hybrid architecture was successfully validated in real world scenario using experimental data from custom built Digital Holographic Microscope. With the advent of newer architectures and hardware, Deep learning networks can further improve the performance in solving inverse problems.

show abstract