BEIJING, Sept. 18, 2023 /PRNewswire/ — WiMi Hologram Cloud Inc. (NASDAQ: WIMI) (“WiMi” or the “Company”), a leading global Hologram Augmented Reality (“AR”) Technology provider, today announced that deep learning is applied to nonlinear holographic image restoration. Actively exploring the application of nonlinear holographic image restoration based on deep learning. The technology utilizes a deep neural network model, and by learning a large amount of hologram data, it can automatically learn the feature of nonlinear distortion and make accurate predictions during the restoration process. Compared with traditional methods, the deep learning-based method can better handle nonlinear distortion, improve the restoration effect, and provide a more accurate database for the subsequent analysis and application of holograms. The deep learning-based nonlinear holographic image restoration has important application value in the field of holographic image processing.

The role of deep learning-based nonlinear holographic image restoration is very important, by learning the nonlinear features of the image and the noise model, deep learning can realize more accurate image restoration and improve the quality and clarity of the image. Specifically, it is mainly reflected in the following aspects:

Feature learning: Deep learning can learn feature representations in images through multi-layer neural networks to extract higher-level features. These features can better describe the structural information and noise models in the image, thus providing a more accurate basis for image restoration.

Nonlinear modeling: Deep learning can model noise in images by constructing complex nonlinear models. These nonlinear models can better capture the distribution and characteristics of noise in an image, leading to more accurate noise removal and image restoration.

Data drive: Deep learning is a data-driven approach that can be trained and learned from large amounts of image data. This allows deep learning to learn more accurate image restoration models from data without the need to manually design complex algorithms.

This nonlinear holographic image restoration includes key modules such as data pre-processing, feature extraction, nonlinear transformation and reconstructed image. First, the input holographic image is pre-processed, such as denoising and downsampling, to improve the restoration effect and reduce the amount of computation. Next, features are extracted from the pre-processed image through CNN. These features can include information such as edges, textures, etc., which are used in the subsequent restoration process. Then, based on the feature extraction, the damaged or missing image information is repaired by introducing nonlinear transformations. This process is usually realized using models such as deep neural networks, whereby by learning a large number of hologram samples, the network can automatically learn the laws of nonlinear transformations. Finally, the repaired hologram is reconstructed based on the repaired features and the nonlinear transform.

By repairing damaged holograms, we are able to restore the details and quality of the image and improve the visualization of the image. This is of great significance for the application and research of holograms and provides strong support for the further development of related fields.

In the research of nonlinear holographic image restoration based on deep learning, in the future, WiMi will carry out in-depth exploration and improvement in the aspects of network structure optimization, dataset expansion, multi-modal fusion, and real-time performance enhancement, in order to further improve the performance and application scope of nonlinear hologram restoration technology based on deep learning.

The current deep learning models still have some limitations when dealing with nonlinear hologram restoration tasks. Future research will be devoted to designing more efficient and accurate network structures to improve restoration results and reduce the consumption of computational resources. For example, it may try to introduce an attention mechanism or an adaptive module to enhance the model’s perceptual ability, so as to better capture the detailed information in the image. In addition, in order to improve the restoration ability of the model, future research will also consider expanding the dataset to include more hologram image data from different scenes and under different lighting conditions. In addition, the introduction of more noise and distortion in real scenes will be considered to increase the model’s adaptability to complex situations.

The nonlinear holographic image restoration task also involves a variety of modalities including phase and amplitude information of the hologram. In the future, WiMi will explore how to better fuse the information of these different modalities to improve the restoration effect. Attempts will be made to introduce a multi-task learning approach to simultaneously learn phase and amplitude restoration to enhance the overall performance of the model. In addition to this, future research will also aim to improve the computational efficiency of deep learning models and enhance real-time performance.

About WIMI Hologram Cloud

WIMI Hologram Cloud, Inc. (NASDAQ:WIMI) is a holographic cloud comprehensive technical solution provider that focuses on professional areas including holographic AR automotive HUD software, 3D holographic pulse LiDAR, head-mounted light field holographic equipment, holographic semiconductor, holographic cloud software, holographic car navigation and others. Its services and holographic AR technologies include holographic AR automotive application, 3D holographic pulse LiDAR technology, holographic vision semiconductor technology, holographic software development, holographic AR advertising technology, holographic AR entertainment technology, holographic ARSDK payment, interactive holographic communication and other holographic AR technologies.

Safe Harbor Statements

This press release contains “forward-looking statements” within the Private Securities Litigation Reform Act of 1995. These forward-looking statements can be identified by terminology such as “will,” “expects,” “anticipates,” “future,” “intends,” “plans,” “believes,” “estimates,” and similar statements. Statements that are not historical facts, including statements about the Company’s beliefs and expectations, are forward-looking statements. Among other things, the business outlook and quotations from management in this press release and the Company’s strategic and operational plans contain forward−looking statements. The Company may also make written or oral forward−looking statements in its periodic reports to the US Securities and Exchange Commission (“SEC”) on Forms 20−F and 6−K, in its annual report to shareholders, in press releases, and other written materials, and in oral statements made by its officers, directors or employees to third parties. Forward-looking statements involve inherent risks and uncertainties. Several factors could cause actual results to differ materially from those contained in any forward−looking statement, including but not limited to the following: the Company’s goals and strategies; the Company’s future business development, financial condition, and results of operations; the expected growth of the AR holographic industry; and the Company’s expectations regarding demand for and market acceptance of its products and services.

Further information regarding these and other risks is included in the Company’s annual report on Form 20-F and the current report on Form 6-K and other documents filed with the SEC. All information provided in this press release is as of the date of this press release. The Company does not undertake any obligation to update any forward-looking statement except as required under applicable laws.