641 results about "View based" patented technology

The invention belongs to the technical field of three-dimensional reconstruction in computer graphics, particularly relates to a sparse view outdoor scene three-dimensional reconstruction method based on multi-view stereo and grids, and aims to solve the problems that input depends on dense views, rendering results are prone to generating fuzzy artifacts, large-scale scene memory occupation is high and the like in the existing reconstruction technology. The method is especially suitable for high-precision reconstruction of an outdoor boundless scene under sparse view input. The method comprises the following implementation steps: acquiring a multi-view image of a scene to be reconstructed and a corresponding camera pose, and determining a scene center based on a K-means clustering algorithm; extracting input view features, generating a cost body based on a multi-view three-dimensional framework, and obtaining scene depth distribution priori by combining a probability depth estimation method; guiding voxel grid sampling based on depth distribution, and mapping light rays exceeding a grid boundary into a limited grid range by using a spatial contraction function; extracting image local features and voxel grid global features for adaptive fusion; and finally, generating a reconstructed image through volume rendering.

The invention provides a three-dimensional model retrieval method based on multi-view aggregation, and the method comprises the steps: 1, designing a three-dimensional model retrieval network based on views, and enabling the three-dimensional model retrieval network to extract the features of a three-dimensional model from the view representation of the three-dimensional model for three-dimensional model retrieval; the three-dimensional model retrieval network MVAT comprises a single-view feature extraction network and a multi-view feature aggregation network, the single-view feature extraction network is responsible for independently extracting local features of a three-dimensional model from each view, and the multi-view feature aggregation network is responsible for generating global feature representation through information fusion of multiple views; 2, weight freezing and contrast learning technologies are introduced, and a three-stage training method is adopted to train the three-dimensional model retrieval network; and 3, performing performance evaluation on the trained three-dimensional model retrieval network on a test set. The three-dimensional model retrieval method has the advantages of being high in feature expression ability, efficient in training method, high in precision and good in generalization.

The invention discloses a target detection method and device based on an aerial view, equipment, a medium and a product. The method comprises the following steps: extracting multi-scale features for an input image of a multi-view-angle surround-view camera; converting the point cloud data of the laser radar into a sparse voxel structure and generating BEV features for voxel features; fusing the multi-scale features and the BEV features to obtain fused BEV features; road topology and semantic information are extracted according to the fused BEV features, and a map is generated; and determining a three-dimensional bounding box and a motion state of the traffic participant according to the fused BEV features and a prediction result of the position of the traffic participant in the map. According to the technical scheme, multi-scale geometric features, BEV features and semantic information are fused, time sequence features of dynamic target detection and static map segmentation are synergetic, the reliability of target detection based on aerial view is improved, and the method is suitable for multi-task BEV perception of three-dimensional object detection, high-precision map segmentation and motion prediction.

The invention discloses a short video recommendation method and system based on multi-modal attention, and relates to the technical field of big data pushing, and the recommendation steps are as follows: S1, obtaining short video watching historical data of a user, dividing a watching behavior into playing duration and a playing completion rate based on the historical data and the watching time of the short video page, respectively endowing weights, and determining the playing duration and the playing completion rate; converting the watching condition of the user into a quantized preference weighting value; and S2, respectively calculating preference emphasis values of different short videos in the historical data, and obtaining a preference threshold value for watching the short videos of the user based on big data analysis. According to the method, active screening is carried out from the pre-generated recommended videos, the recommendation accuracy is further improved, the current specific requirements of the user are met, the videos with large differences are introduced as candidates to perfect the push list, the correlation between the recommended videos and user preferences is ensured, the diversity of recommended contents is increased, and the user experience is improved. And aesthetic fatigue caused by the fact that the user sees too many similar videos is avoided, and user experience is improved.

The embodiment of the invention provides a sample set construction method, a question and answer model training method, a question and answer processing method, a request processing method and a task platform, and the sample set construction method comprises the steps: inputting a sample image into an image annotation model, and obtaining a global annotation result of the sample image; identifying a target object in the sample image, marking the target object in the sample image based on an obtained identification result to obtain a global view, and intercepting the target object to obtain a local view; the global view, the local view and visual prompt information are input into the image annotation model, a local annotation result of the sample image is obtained, and the visual prompt information is used for prompting the image annotation model to execute an annotation task on the global view based on the local view; and constructing a sample set based on the sample image, the global labeling result and the local labeling result. According to the method, the accuracy and the comprehensiveness of the annotation result of the image can be improved.

The invention discloses a method for realizing element positioning in an RPA system, which comprises the following steps of: 1, obtaining an original request input by a user and a current webpage of the user, and obtaining a view relation graph by utilizing the webpage; 2, recognizing similar elements according to the view relation graph; splitting the original request into a condition judgment instruction or a loop execution instruction; step 3, acquiring element coordinates for the loop execution instruction based on the view relation graph; step 4, disassembling the condition judgment instruction into an element query; then recalling visible elements to be recognized in the similar elements; and step 5, for the visible elements to be identified, acquiring element coordinates by using the view relation graph or the multi-modal large model. According to the invention, element positioning can be rapidly realized in the RPA working process, and the misjudgment condition is reduced at the same time.

The invention discloses a volume video intelligent coding method, and the method comprises the steps: a feature enhancement module based on view guidance is used for carrying out the feature enhancement of self-adaptive learning anchor features; the progressive entropy coding module based on context guidance is used for performing efficient compression coding on the enhanced anchor point features; the Gaussian attribute feature decoder is used for obtaining each neural Gaussian attribute; and through a neural Gaussian sputtering rendering technology, the neural Gaussian is mapped to a target visual angle, and a high-quality reconstructed viewpoint image is generated. According to the method, the scene information of each view angle is fused into the feature learning process, and the Gaussian attribute progressive coding strategy is constructed, so that the compression efficiency of the volume video is improved.

The invention provides a dynamic three-dimensional scene reconstruction and rendering system and method and related equipment, and the method comprises the steps: receiving a monocular video sequence through an image encoder, and carrying out the visual feature extraction of each frame of image; the scene generator constructs a three-plane structure expression aligned with the view angle of the current camera based on the multi-frame visual features extracted by the image encoder, performs time coding on the multi-frame visual features and maps the multi-frame visual features to the three-plane structure expression to generate a three-dimensional scene feature expression; and the scene decoder decodes the three-dimensional scene feature representation and generates a composite image under a corresponding view angle based on a volume rendering mechanism, and the composite image can display geometric details of the scene under different view angles and maintain geometric consistency under different view angles. Modeling and rendering of the dynamic three-dimensional scene are achieved through the monocular video sequence, multi-view input or prior scene information does not need to be depended on, and the adaptive capacity and generalization performance of the system in a rapid change environment are effectively improved.

The invention discloses a three-dimensional modeling method, electronic equipment, a storage medium and a computer program product, and relates to the technical field of data processing, and the method comprises the steps: retrieving a four-dimensional bilateral affine grid based on a spatial dimension index and a color dimension index of a three-dimensional Gaussian point of a training view to obtain an affine transformation matrix, adjusting the color dimension index through the affine transformation matrix to obtain an adjusted color dimension index; rendering the training view based on the adjusted color dimension index through a three-dimensional Gaussian splash model to obtain a rendered image; and based on the luminosity loss between the rendering image and the training view, performing parameter optimization on the four-dimensional bilateral affine grid and the three-dimensional Gaussian splash model to obtain an optimized three-dimensional Gaussian splash model, and performing three-dimensional modeling on the multi-view image based on the optimized three-dimensional Gaussian splash model. According to the method, the floating objects in the scene are reduced, and the geometric modeling accuracy of the scene is improved, so that the rendering quality and the reconstruction accuracy in the three-dimensional modeling process are improved.

The invention provides a multi-view camera image and laser radar fused road perception method and system. The method comprises the steps of obtaining depth information features of a camera aerial view and depth information features of a laser radar aerial view based on a vehicle-mounted camera multi-view image and laser radar point cloud data; obtaining camera aerial view features with depth distribution based on the depth information features of the camera aerial view and the depth information features of the laser radar aerial view; performing feature alignment on the camera aerial view features with depth distribution and the camera aerial view features without depth distribution to obtain camera aerial view image features with depth information representation; and obtaining a prediction result based on the camera aerial view image features containing the depth information representation and the depth information features of the laser radar aerial view. According to the invention, the road condition of the current scene is inferred and predicted in real time through the image of the vehicle-mounted camera during vehicle driving, and the current driving road condition is sensed in real time under the unstructured road condition with limited visual field and severe environment.

Data platforms described herein are configured to monitor a compute environment and provide a user interface. Such a data platform may direct an application to process, on a user interface computing thread, user input to a graphical user interface view that is rendered based on data received from a data platform, to detect, on the user interface computing thread, a set of instructions associated with a visualization of a logical graph, to determine that the set of instructions satisfies one or more criteria, to execute, based on the set of instructions satisfying the one or more criteria, the set of instructions on a set of additional computing threads, and to render the visualization of the logical graph in the graphical user interface view based on the processing of the user input and the executing of the set of instructions. Corresponding methods, systems, and products are also disclosed.

A method and apparatus generate a 2-dimensional (2D) image. A method for generating a 2-dimensional (2D) image includes obtaining a time index and a view. The method further includes obtaining first coding indices and a first codebook for canonical 3D Gaussians, wherein the canonical 3D Gaussians are 3D Gaussians corresponding to a reference time index, and represent a 3D space corresponding to the reference time index. The method also includes obtaining second encoding indices and a second codebook for a parameter offset, wherein the parameter offset indicates a difference between the canonical 3D Gaussians and 3D Gaussians for the time index. The method further includes reconstructing the canonical 3D Gaussians based on the first coding indices and the first codebook. The method also includes reconstructing parameter offsets of the 3D Gaussians for the time index based on the second coding indices and the second codebook. The method further includes adding the reconstructed canonical 3D Gaussians and the reconstructed parameter offset to reconstruct the 3D Gaussians for the time index. The method also includes generating a second image for the view based on the reconstructed 3D Gaussians.

Methods and systems for training an end-to-end autonomous driving system using a vision-language planning (VLP) machine learning model in a closed-loop environment. Images associated with an environment about a vehicle are generated, and a BEV model is executed to generate a BEV view based on the images. A planning model predicts navigation trajectories based on the BEV. The VLP model enhances the system by extracting vision-based planning features, generating text prompts, and employing a language encoder to create text-based expectation features. A contrastive learning model identifies similarities between vision and text features, boosting the performance of the BEV and planning models. The system undergoes closed-loop evaluation in a simulated environment, capturing metrics to refine the autonomous driving system.

The invention relates to a data government method and system for digital government affairs, and relates to the technical field of digital government affairs, and the method comprises the steps: parsing SQL statements and corresponding table structures of different databases in a digital government affair system based on a constructed SQL parser to obtain data operation information; constructing a global data relation view according to the analyzed data operation information; based on the global data relationship view, deploying monitoring points on a data flow path to track data flow changes on the data flow path; when it is detected that the data flow changes, abnormal data are recognized according to the field mapping relation, the processing logic and the dependency relation recorded in the global data relation view; and repairing the identified abnormal data according to a repairing strategy. The method has the advantages that the abnormal data can be quickly recognized, and processing is carried out according to the repair strategy.

A method for providing an augmented reality view includes obtaining, based on a location of a computing device, a three-dimensional (3D) reconstruction of a scene associated with the location, the 3D reconstruction of the scene including one or more objects, processing the 3D reconstruction of the scene by generating one or more virtual objects which respectively correspond to the one or more objects, each virtual object being in a form of a virtual outline of a corresponding object among the one or more objects and, providing, for presentation on a display device of the computing device, an augmented reality view of the scene by overlaying at least one virtual outline onto a corresponding real-world object presented on the display device such that the at least one virtual outline at least partially frames the corresponding real-world object.

The invention provides a CT (Computed Tomography) equiangular data acquisition method and system, a storage medium and a CT scanning system. The method comprises the following steps: acquiring an offset error of a rotor encoder of the CT scanning system; calculating a compensation amount of the rotor encoder based on the offset error; after the compensation amount is delayed at a theoretical trigger signal of the data measurement system of the CT scanning system, a corrected trigger signal is sent out; and correcting the data acquisition of the current view based on the triggering interval of the previous view of the CT scanning system. According to the CT equiangular data acquisition method and system, the storage medium and the CT scanning system, equiangular data acquisition of the CT scanning system is realized through rotor encoder error compensation and rotor speed error compensation.

Provided are a lens assembly and an electronic device including the lens assembly, the lens assembly including a first reflector configured to rotate around a first rotation axis, a second reflector configured to rotate around a second rotation axis, a plurality of lenses, and an image sensor configured to generate a plurality of captured images having different capturing views based on a rotation of at least one of the first reflector or the second reflector, in which the first reflector, the second reflector, the plurality of lenses, and the image sensor are provided in sequential order from an object's side.

A refuse vehicle includes a chassis, a body coupled to the chassis and defining a refuse compartment, a lift assembly configured to lift a refuse container to dump contents thereof into the refuse compartment, a display interface, a plurality of cameras positioned to capture a plurality of different views from the refuse vehicle, and a controller. The controller is configured to assign priority values to the plurality of different views, compare the priority values, and display, on the display interface, at least one of the plurality of different views based on the comparison of the priority values.

The invention belongs to the technical field of three-dimensional measurement, and discloses a power transmission line icing volume measurement method, system and device, a medium and a program product, and the method comprises the steps: employing a binocular camera to shoot and correct an icing power transmission line view, and obtaining internal and external parameters, performing depth estimation on the power transmission line view based on the corrected power transmission line view and the internal and external parameters, training a conductor detection model and inputting the corrected power transmission line view to obtain a detection frame and a corresponding confidence coefficient, using the detection frame with the highest confidence coefficient as a prompt, inputting the prompt and the corrected power transmission line view into an SAM2 network for segmentation, and obtaining a segmentation result; de-noising and morphological processing are carried out on the masks of the ice-coated wires, and finally the ice-coated area of the power transmission line is calculated. The system, the equipment and the medium are used for implementing the method. The program product comprises a computer program for implementing the method; the method for measuring the icing volume of the power transmission line has the effects of stability, reliability, high efficiency, accuracy and high safety.

A cybersecurity system provides the ability to detect security risks in a cross-platform cloud solution. A unified data schema is used to abstract resources, principals and others across multiple platforms. A security graph is generated to present a unified view of cloud environments, which are then easily queried using the structure of the data schema. The solution allows a compact representation of cloud environments, which is scalable and multi-layered. The security graph allows for representation of production environments, staging environments, as well as code for deploying workloads in the cloud environment. Thus the solution is also able to present a complete picture of a user's entire cloud environment. The solution further allows to generate subgraph views, by associating a tag to certain nodes, then rendering a view based on nodes which include the tag, and all children nodes thereof.

The invention provides a method and device for evaluating output of a large language model, a medium and a product. The method for evaluating the output of the large language model comprises the following steps: extracting one or more key viewpoints from the output of the large language model, wherein each key viewpoint comprises a self-consistent fact statement; constructing an adaptive thinking tree based on the extracted key viewpoints to split each key viewpoint into a plurality of verifiable sub viewpoints; retrieving evidence data associated with the plurality of sub-viewpoints from one or more external information sources, and verifying the plurality of sub-viewpoints according to the retrieved evidence data; in response to the fact that the verification of the multiple sub viewpoints has ended, integrating the verification results of the multiple sub viewpoints, and determining an evaluation result of the corresponding key viewpoint according to the integrated verification results of the multiple sub viewpoints; and outputting the evaluation result of each of the key viewpoints and the corresponding evidence data.

A computer system displays a first view of a three-dimensional environment, including a first user interface object, that when activated by a user input meeting first criteria, causes performance of a first operation. While displaying the first view, the computer system detects first movement of a hand in a physical environment, and in response, changes an appearance of the first user interface object in the first view based on the first movement, including: in accordance with a determination that the first movement meets the first criteria requiring the hand move in a first manner, performing and indicating performance of the first operation; and in accordance with a determination that the first movement does not meet the first criteria, moving the first user interface object away from a position in the three-dimensional environment corresponding to a location of the hand in the physical environment without performing the first operation.

The invention belongs to the field of visual training, and discloses a dynamic visual training method and system based on naked eye 3D imaging, electronic equipment and a storage medium, and the method comprises the steps: obtaining real-time motion information of eyeballs of a user, and analyzing the real-time motion information to obtain a visual angle change parameter of the user; based on the view angle change parameters, performing feature extraction and matching on input left and right view images by using a parallax estimation algorithm to obtain a pixel-level virtual view; performing dynamic rendering based on the pixel-level disparity map to obtain a 3D view; and generating a training task, selecting the 3D view based on the training task, and training the dynamic vision of the user. According to the invention, an artificial intelligence algorithm is designed by adopting a modular architecture, online learning and updating are supported, intelligent and personalized visual training is realized, and the visual cognition ability of the user can be effectively improved.

The invention provides a high-quality map multi-modal data set making method based on POI data, and the method comprises the steps: setting a map range and a map scaling, calculating the range of each map view under the current map scaling, and counting the number of the map views; reading map view information, and displaying the current map view; obtaining POI data in the current map view field, and displaying the POI as a map picture in the current map view field by using an icon; selecting a POI type, and generating an expression text for expressing a map view POI condition based on the type, the number and the distribution condition of the POI; and traversing all map views in the map range, and generating a map picture and an expression text of the map range. The technical problems that in the prior art, manual map text expression is low in efficiency, time-consuming and labor-consuming, and the precision requirement of large model training for large-scale data is difficult to meet can be solved.

A method for controlling autonomous driving of a vehicle is introduced. The method may comprise, training, based on an inference depth and an inference pose, a synthetic image model for generating a synthetic image, generating, based on the synthetic image, a first virtual image to be associated with the original image, generating, based on the original image, a second virtual image, training a generative adversarial network (GAN) for determining, based on the original image, authenticity of the first virtual image and the second virtual image, training, based on the trained GAN, a depth network, wherein the trained GAN outputs a determination of the authenticity of the first virtual image, outputting, based on the trained depth network, signal, and controlling, based on the signal, autonomous driving of the vehicle.

The invention provides a multi-modal interactive tourism recommendation method, system and device and a medium, and belongs to the technical field of tourism interaction, and the method comprises the steps: constructing a user tourism portrait based on the combination of clustering and anomaly detection; according to the clustering result and the user behavior data, constructing user portrait labels and feature descriptions, and configuring the constructed user portraits into a multi-modal interaction module; an interaction interface unit, a voice recognition unit, an image recognition unit and a gesture control and interaction unit are configured based on the multi-mode interaction module; the multi-mode interaction module generates a VR panorama based on voice information, image information and gestures input by a user, and feeds back the VR panorama to the interaction interface unit in cooperation with voice and touch. An interactive interface is provided through a virtual reality technology, so that a user can perform customization operation of using the embodiment without perception, the user experience is improved, and more intuitive and immersive destination and recommendation place information experience is obtained.

Several examples, systems, and methods are disclosed that involve the dynamic reconstruction of new views, at least partially based on flow rematching. A first computing system can cause an image rendering model to generate an estimated image of a scene based on at least a plurality of images of the scene. The at least one image in the plurality of images can be from at least one different time or view. The first computing system can update the image rendering model based on at least the estimated image, the plurality of images, and / or one or more motion criteria associated with the estimated image.

The invention discloses a multi-dimensional tree form control generation method and device, and relates to the field of data processing. The method comprises the steps of obtaining a flattened original data array, an expandable dimension array, a maximum dimension hierarchy and a configuration object issued by a background; initializing a core data structure; original data and all nodes are traversed, father nodes are searched, the relation is established, and a two-channel tree structure is constructed; generating and rendering a table view based on the constructed tree structure; and in response to user interaction, dynamically unfolding and folding table nodes by maintaining inter-row reference and folding states. According to the method, the natural hierarchy and the interactive expansion hierarchy of the data are separated through the dual-channel tree structure, and the problems of hierarchical disorder, low rendering efficiency and slow interactive response of a traditional tree table during multi-dimensional data analysis are solved by utilizing a path key mapping and state local updating mechanism; efficient and flexible multi-dimensional data display and interaction are realized, and the method is suitable for enterprise-level data analysis scenes.

The invention discloses a materialized view construction method, a data processing system, a medium and a program product, and relates to the field of electrical digital data processing.The method comprises the steps that text query information is received, the execution sequence and the execution type of query operation in the text query information are determined, and a logic plan is generated; extracting a scanning operation, a projection operation, a connection operation and an aggregation operation from the logic plan to obtain a query sub-plan representing query semantics; according to the operation type of the query sub-plan, converting the query sub-plan into an initial plan slice; normalizing the initial plan film to generate a standard plan film in a preset format; according to a preset aggregation strategy, performing deduplication merging processing on the standard plan slices to obtain a target plan slice; and generating a table establishment statement of the materialized view based on the target plan film to construct the materialized view. By implementing the method, generation of the materialized view can be optimized, and the redundancy of the materialized view is reduced.

The invention discloses an intelligent algorithm development auxiliary tool for a Lingpivot plasma control system, which belongs to the technical field of plasma control systems and comprises a visualization module, an AI question and answer module and a WebView panel. The visualization module is used for analyzing a PCS project directory, generating an interactive view based on WebView, and supporting architecture analysis, file generation, code navigation and bidirectional editing synchronization; the AI question and answer module adopts a locally deployed retrieval enhancement generation system and is combined with a PCS knowledge vector database to provide field-specific query answers; and the WebView panel is used for serving as an interactive page of a user with the visualization module and the AI question and answer module, rendering a tree view and an organizational structure diagram of the visualization module, and displaying questions and answers of the AI question and answer module. According to the method, complex parameter configuration and multi-file management are simplified, and the operation time is remarkably shortened.