9 results about "Video restoration" patented technology

This invention discloses a data processing method, system, device, and medium based on a user-selected local model. The method includes: acquiring a local machine learning model file in response to a user operation; dynamically parsing model metadata to determine input and output specifications; acquiring multimodal target data and preprocessing and adapting it according to the input specifications; calling local hardware resources to execute model inference; parsing the inference results according to the output specifications and outputting them to the target business system. This invention overcomes the closed nature of traditional software-built-in AI models, achieving full utilization of local AI computing power and effective privacy protection of sensitive data. Through a highly abstract underlying adaptation architecture, this invention is not dependent on specific application scenarios and can be widely integrated as a general-purpose underlying technology into various industry software such as video restoration, medical image analysis, professional image retouching, and industrial inspection, giving the software flexible AI capability scalability.

This disclosure relates to a training method, apparatus, electronic device, storage medium, and program product for a video restoration model. The training method for the video restoration model includes: training an image restoration model based on a first training sample set to obtain an initial video restoration model, wherein the first training sample set includes multiple training videos; and training the initial video restoration model based on a second training sample set to obtain a final video restoration model, wherein the second training sample set includes multiple training images and multiple training videos.

This invention discloses a real-time masking system and method for scenes inside windows during drone delivery, belonging to the fields of video processing, artificial intelligence, and drone delivery technology. The system comprises eight modules: drone mounting, video acquisition, AI target detection, masking parameter configuration, masking processing, edge optimization, data storage, and control. The method, based on this system, achieves fully automated masking throughout the entire process. It can accurately distinguish between areas inside and outside the window, masking private areas inside the window in real time with a masking response time ≤0.5 seconds and a transmission delay ≤1 second. Edge feathering optimization eliminates abruptness, supports original video restoration and private storage, balancing privacy protection, delivery efficiency, and compliance requirements. It is applicable to various drone last-mile delivery scenarios, demonstrating strong practicality and scalability.

The method, apparatus, storage medium, and computer equipment for restoring film and television scripts provided in this application first obtain the video list and breakpoint information corresponding to the target drama title during script restoration. Based on the breakpoint information, the video to be restored for the current episode is determined from the video list, along with the historical plot synopsis and character profiles already generated for the target drama title, enabling resume playback from breakpoints. Next, a script information extraction model is used to analyze and process this data, obtaining the episode's metadata and plot text. The episode's metadata allows for updating the historical plot synopsis and character profiles, while the plot text updates the script output file in the database, ensuring logical coherence and consistency in character settings. After the current episode's video restoration is complete, the next episode's video is retrieved from the video list and used as the new current episode's video for script restoration, continuing until the script restoration of the last episode in the video list is complete, resulting in a complete script output file.

The application discloses a structural health monitoring video recovery method based on flexible deep learning and belongs to the technical field of video recovery.The method comprises frame sampling, flexible error elimination, frame initial recovery and deep compensation recovery steps.In the frame sampling, a sampling matrix can be optimized in combination with a recovery process through a convolution layer.In the flexible error elimination, a flexible deep network embedded with an adjustable noise level diagram can eliminate various environmental noises.In the frame initial recovery and deep compensation recovery, the spatiotemporal correlation of non-key frames is enhanced by using key frames, so that the lost video information is recovered to the maximum extent.The application realizes joint optimization of sampling and recovery by constructing an interpretable deep learning framework, can restore the video with high fidelity even under the condition of low data retention rate, and significantly reduces the hardware dependence.

The application relates to a video restoration method, comprising the following steps: pre-training a generative video restoration network based on large-scale high-quality video data to obtain a basic model with strong detail generation capability; constructing a reference image set and extracting an attribute set through an attribute extractor; preparing a training target high-definition video corresponding to the reference image, synthesizing a low-definition video and calculating a supervision loss; freezing the basic model weight obtained through pre-training to perform restoration under attribute condition constraints; inputting a real low-definition video and a target object attribute set to generate a high-resolution video and realize consistent industrial-level restoration output of the target object; and the application also relates to a video restoration system. The application can keep the consistency of target object attributes in cross-lens and long-time sequence segments while keeping high perceptual quality.

The utility model relates to the technical field of accident identification equipment, and specifically relates to a multifunctional calibration device for accident scene video restoration. The multifunctional calibration device comprises a calibration chassis, a calibration rod and a positioning mechanism. The calibration chassis is provided with rolling wheels at the bottom, and a calibration grid is formed on the calibration chassis. The calibration rod is movably arranged on the upper side of the calibration chassis through the calibration grid. The positioning mechanism is movably arranged on the four corners of the calibration chassis. The device can simulate the chassis of an accident vehicle, dynamically or statically calibrate the position, form continuous data, facilitate accident video restoration, and improve the measurement accuracy and efficiency. The device solves the problems of limited calibration accuracy, missing dynamic data, inconvenient on-site operation and serious scene interference of the existing restoration means.

This invention provides a video restoration region localization method and related equipment, relating to the field of video restoration technology. It extracts high-frequency residual features from training noise stream data and performs early fusion of these features with the original pixel features in the training RGB stream data to capture the correlation features between content and noise. A loss function is calculated based on a set supervision mode and a dense prediction mask sequence, and the network parameters of the 3D Swin-UNet with a spatiotemporal attention mechanism are updated based on the loss function value. This eliminates optical flow dependence and effectively solves the problems of existing video restoration detection methods when facing modern deep learning restoration algorithms, such as failure to detect low-contrast regions, loss of small target forgery traces, low inference efficiency due to excessive reliance on optical flow features, and excessive dependence on massive frame-by-frame labeled data in fully supervised training. It achieves efficient and accurate localization under sparse temporal supervision.