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.
Iterative methods could provide high-quality image reconstruction for Fourier-domain optical coherence tomography (FD-OCT) by solving an inverse problem. Compared with the regular IFFT-based reconstruction, a more accurate estimation could be iteratively solved by integrating prior knowledge, however, it is often more time-consuming. To deal with the time problem, we proposed a fast iterative method for FD-OCT image reconstruction empowered by GPU acceleration. An iterative scheme is adopted, including a forward model and an inverse solver. Large-scale parallelism of OCT image reconstruction is performed on B-scans. We deployed the framework on Nvidia GeForce RTX 3090 graphic card that enables parallel processing. With the widely used toolkit Pytorch, the inverse problem of OCT image reconstruction is solved by the stochastic gradient descent (SGD) algorithm. To validate the effectiveness of the proposed method, we compare the computational time and image quality with other iterative approaches including ADMM, AR, and RFIAA method. The proposed method could provide a significant speed enhancement of 1,500 times with comparable image quality to that of ADMM reconstruction. The result indicates a potential for high-quality real-time volumetric OCT image reconstruction via iterative algorithms.
The image reconstruction for Fourier-domain optical coherence tomography (FD-OCT) could be achieved by iterative methods, which offer a more accurate estimation than the traditional inverse discrete Fourier transform (IDFT) reconstruction. However, the existing iterative methods are mostly A-line-based and are developed on CPU, which causes slow reconstruction. Besides, A-line-based reconstruction makes the iterative methods incompatible with most existing image-level image processing techniques. In this paper, we proposed an iterative method that enables B-scan-based OCT image reconstruction, which has three major advantages: (1) Large-scale parallelism of the OCT dataset is achieved by using GPU acceleration. (2) A novel image-level cross-domain regularizer was developed, such that the image processing could be performed simultaneously during the image reconstruction; an enhanced image could be directly generated from the OCT interferogram. (3) The scalability of the proposed method was demonstrated for 3D OCT image reconstruction. Compared with the state-of-the-art (SOTA) iterative approaches, the proposed method achieves higher image quality with reduced computational time by orders of magnitude. To further show the image enhancement ability, a comparison was conducted between the proposed method and the conventional workflow, in which an IDFT reconstructed OCT image is later processed by a total variation-regularized denoising algorithm. The proposed method can achieve a better performance evaluated by metrics such as signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), while the speed is improved by more than 30 times. Real-time image reconstruction at more than 20 B-scans per second was realized with a frame size of 4096 (axial) × 1000 (lateral), which showcases the great potential of the proposed method in real-world applications.
Current learning-based single image super-resolution (SISR) algorithms underperform on real data due to the deviation in the assumed degradation process from that in the real-world scenario. Conventional degradation processes consider applying blur, noise, and downsampling (typically bicubic downsampling) on high-resolution (HR) images to synthesize lowresolution (LR) counterparts. However, few works on degradation modelling have taken the physical aspects of the optical imaging system into consideration. In this paper, we analyze the imaging system optically and exploit the characteristics of the real-world LR-HR pairs in the spatial frequency domain. We formulate a real-world physics-inspired degradation model by considering both optics and sensor degradation; The physical degradation of an imaging system is modelled as a low-pass filter, whose cut-off frequency is dictated by the object distance, the focal length of the lens, and the pixel size of the image sensor. In particular, we propose to use a convolutional neural network (CNN) to learn the cutoff frequency of real-world degradation process. The learned network is then applied to synthesize LR images from unpaired HR images. The synthetic HR-LR image pairs are later used to train an SISR network. We evaluate the effectiveness and generalization capability of the proposed degradation model on real-world images captured by different imaging systems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.