102 results about "Geometry processing" patented technology

A video compression system and method integrates geometric compression with cognitive understanding through a persistent cognitive machine interface. The system employs a hierarchical encoder generating multi-scale compressed representations organized within a Lorentzian manifold structure. A geometric processor maintains temporal causality through time-like geodesics and light cone constraints while organizing video content according to semantic relationships. A cognitive interface creates thought bundles as navigable submanifolds, enabling semantic access to compressed content beyond traditional temporal indexing. The system supports real-time processing through progressive refinement, streaming coarse representations immediately while adding detail in parallel. Symbolic anchors mark semantically significant points, enabling concept-based navigation through compressed video. Federated learning capabilities allow distributed systems to share geometric patterns while preserving content privacy. The architecture enables improved compression ratios while maintaining both temporal causality and semantic navigability, transforming video from sequential media into an intelligently accessible information space.

The invention discloses a target detection pre-labeling method based on a fast algorithm, and relates to the technical field of computer vision and geometric processing, and the target detection pre-labeling method based on the fast algorithm comprises the following steps: S1, data acquisition and preprocessing; and the collected image data is transmitted to a cloud data center in real time through wireless transmission. According to the target detection pre-labeling method based on the fast algorithm, image information can be locked and recognized more accurately through operation of two times of pre-labeling, so that the collected image information can be recognized and screened more accurately, a certain workload can be reduced for subsequent manual auditing and correction, and the accuracy of target detection and pre-labeling is improved. And meanwhile, it is also ensured that the pre-labeling model can carry out accurate labeling processing on a relatively fuzzy or shielded image, and through operation of a YOLOv5 algorithm, the pre-labeling model can be more efficient and faster when carrying out image recognition.

A graphics processing unit (GPU) and method for processing primitives using a rendering space subdivided into a plurality of tiles are described herein. The GPU includes geometry processing logic that includes a plurality of geometry pipelines and a block back-end module. The geometry pipeline is configured to receive a batch of primitives of the sequence of primitives. Each of the geometric pipelines includes: one or more geometric processing modules configured to perform one or more geometric processing functions on the primitives in a batch of primitives received at the geometric pipeline; and a tile front-end module configured to determine, for each tile in a set of one or more tiles, one or more tile-primitive indications, the one or more tile-primitive indications indicate which of the primitives of the batch of primitives received at the geometric pipeline are present within the tile.

Systems and methods to efficiently get precision geometry for a graphic object on a thin client application such as running on a browser or hand-held device. Specifically, a Precision Geometry Client running on a client device sends requests to a corresponding Precision Geometry Service running on a server system to obtain precision geometry primitives that the client device, thereby offloading the processor-intensive precision geometry processing from the client to the server system.

The invention discloses a clinical operation data analysis method based on virtual reality, and belongs to the field of virtual reality technology and medical skill training. Comprising the following steps: constructing a high-dimensional interaction data tensor covering space-time sequence features; establishing a three-dimensional space topological relation graph based on medical scene understanding, mapping various clinical operation skills into a three-dimensional model interaction sequence of a virtual medical device and an anatomical structure, and generating a multi-dimensional operation behavior feature vector matrix; virtual instrument operation sequence fragments with abnormal interaction efficiency or operation track deviation are identified, and dynamic loading priority weights of virtual medical scene resources are determined according to the virtual instrument operation sequence fragments; when the rendering frame rate of the virtual scene is lower than a specified threshold value, generating early warning information; and in a double-layer adaptive medical scene rendering optimization process, identifying performance bottleneck nodes and geometric processing conflicts in a three-dimensional rendering pipeline, and carrying out dynamic shader scheduling and model detail automatic switching according to a priority rule.

Some embodiments of a method may include a learning-based point cloud geometry processing block method, the method including: accessing a first feature map, wherein the first feature map has a quantity of C channels and is an input to the processing block, and wherein the first feature map is generated by a first set of neural network layers; accessing a set of distribution parameters; transforming the first feature map to a second feature map based on the set of distribution parameters; and encoding the second feature map into a bitstream. These example processes may be applicable to both the encoder and the decoder of an AI-based point cloud compression (PCC) framework.

The invention relates to a method (50) comprising the steps of: - using a sensor to acquire (110) an image of the sample composed of grains; - applying (120), to the image (1), a convolutional neural network in order to obtain a contour map (C) associating, with each pixel of the image, a value equal to one unit when that pixel belongs to a contour of a grain and otherwise equal to zero; - applying (130), to the contour map (C), a segmentation algorithm in order to obtain a segmented image (S) comprising a plurality of regions, one region being separated from a neighbouring region by a contour having a thickness of a single pixel; and - applying (140), to the segmented image (S), one or more geometric processing operations in order to calculate physical quantities for each grain so as to characterise the lithology of the sample (3).

Systems and methods to efficiently get precision geometry for a graphic object on a thin client application such as running on a browser or hand-held device. Specifically, a Precision Geometry Client running on a client device sends requests to a corresponding Precision Geometry Service running on a server system to obtain precision geometry primitives that the client device, thereby offloading the processor-intensive precision geometry processing from the client to the server system.

The invention discloses a geometric processing method and system, a processor, equipment, a medium and a product, and the method comprises the steps: carrying out the first-stage geometric processing of a to-be-processed first vertex, and obtaining a second vertex; performing second-stage geometric processing on the second vertex to obtain data after geometric processing; wherein the geometric processing of the first stage is used for removing the vertexes, which do not need to be subjected to coloring processing, in the first vertexes based on a primitive removal mode, so as to obtain second vertexes; the geometric processing of the second stage is a geometric processing process aiming at the second vertex, and the geometric processing of the first stage lacks the coloring processing compared with the geometric processing of the second stage. Based on the embodiment provided by the invention, the overall performance of geometric processing can be optimized by combining staged vertex elimination and coloring processing.

The invention provides a graphic processing method and device, electronic equipment and a storage medium, the method is applied to the electronic equipment, the electronic equipment comprises a plurality of graphic processing modules and a storage module, and for any graphic processing module, the method comprises the following steps: under the condition that the graphic processing module receives a drawing instruction, the graphic processing module sends the drawing instruction to the electronic equipment; according to the mapping serial number of the graphic processing module, fragment entry information of a to-be-processed first vertex fragment of the graphic processing module is read from the storage module, and the fragment entry information comprises a fragment starting position, a fragment ending position and splitting state information; acquiring a first vertex fragment according to the fragment starting position and the fragment ending position; performing primitive splitting on the first vertex fragment according to the primitive topological information and the splitting state information of the first vertex fragment, and determining a first primitive splitting result; and performing geometric processing on the first primitive splitting result to obtain a primitive processing result of the first vertex fragment. The embodiment of the invention can improve the overall processing efficiency of the system.

The application relates to the technical field of integrated circuit design and verification, in particular to a service test system for a texture block level, which generates a plurality of accurate controllable screen coordinates through a simulation geometry processing module and a simulation rasterization module and provides the screen coordinates to a texture processing module, so that the texture processing module can independently verify the logic of texture processing based on the generated screen coordinates, the reliability of the texture processing module does not need to be tested through system-level verification for service testing, the test requirement is lowered to the texture block level, thus the workload of system-level testing can be saved, the influence of problems of other modules on the texture processing module testing is avoided, the test difficulty is reduced, and the test efficiency and problem positioning accuracy of the texture block level service test are improved.

The present disclosure provides a graphics processing method, apparatus and system, a computing device, and a storage medium. The method is executed by a topology splitting module in a target graphics processing core, and comprises: acquiring a graphics drawing command, the graphics drawing command indicating that a graphic having a specified topology type is to be drawn; on the basis of the graphics drawing command, acquiring vertex index data required for drawing the graphic; on the basis of the specified topology type, dividing the vertex index data into primitive packets according to index order, to determine a primitive packet to be processed by the target graphics processing core, and inserting a corresponding synchronization marker; transmitting the primitive packet to be processed by the target graphics processing core and the corresponding synchronization marker to a geometry processing pipeline module in the target graphics processing core for processing, to obtain a geometry processing result having the synchronization marker, wherein the geometry processing result having the synchronization marker is processed by a pixel processing pipeline module in the target graphics processing core to obtain a visual graphic.

The application discloses a graphics processor, a primitive output method, a chip, a server and electronic equipment, and belongs to the chip field.The graphics processor comprises a geometry processing pipeline;the geometry processing pipeline is used for performing graphics drawing based on a first drawing instruction to obtain a drawing result, the drawing result comprising primitive data of at least two primitive types, the at least two primitive types comprising at least two of points, lines and triangles, and the first drawing instruction being used for instructing the geometry processing pipeline to realize the function of geometry processing in a grid shading rendering pipeline.In the application, the primitive data of multiple primitive types can be obtained by only one drawing instruction, the performance of the graphics processor is saved by avoiding repeated drawing by multiple drawing instructions to obtain the primitive data of multiple primitive types.

A method of rendering, in a rendering space, a scene formed by primitives in a graphics processing system. A geometry processing phase includes the step of storing fragment shading rate data representing a first fragment shading rate value and associating data identifying a primitive with the fragment shading rate data. A rendering phase includes the steps of retrieving the stored fragment shading rate data and associated data identifying the primitive, obtaining an attachment specifying one or more attachment fragment shading rate values for the rendering space; processing the primitive to derive primitive fragments to be shaded; and for each primitive fragment, combining the first fragment shading rate value for the primitive from which the primitive fragment is derived with an attachment fragment shading rate value from the attachment to produce a resolved combined fragment shading rate value for the respective fragment.

The invention discloses a real-time 3D scene modeling system based on physical rendering. The real-time 3D scene modeling system comprises a scene data acquisition module, a geometric processing and reconstruction module, a material attribute extraction and processing module, a dynamic illumination acquisition and analysis module, a real-time physical rendering engine module and a rendering output and post-processing module. Real-time scene geometry and material data capture, physical law-based material and illumination model construction and an efficient real-time rendering engine are integrated, an image with a high physical reality sense is output on the premise that the interaction frame rate is kept, the system can automatically or semi-automatically process real world scene information, and the real world scene information processing efficiency is improved. According to the method, the three-dimensional content is converted into a digital model with rich physical attribute description, and an optimized real-time physical rendering algorithm is used for drawing, so that the visualization quality and immersion of real-time application are greatly improved, the dependence on manual adjustment of professional art designers is reduced, and the production efficiency and the automation degree of the three-dimensional content are improved.

The invention discloses a processor, a drawing method, a chip and electronic equipment, and belongs to the field of chips. The processor comprises a task generation unit, at least two parallel geometric processing assembly line units, an output rearrangement unit and a pixel processing assembly line unit. The task generation unit is used for splitting a received drawing instruction into a plurality of task packages and distributing the plurality of task packages to one or more geometric processing pipeline units in the at least two geometric processing pipeline units; the geometric processing assembly line unit is used for processing the received task package to obtain a coloring result and outputting the coloring result to the output rearrangement unit; and the output rearrangement unit is used for sorting the plurality of coloring results corresponding to the plurality of task packages according to the distribution sequence of the plurality of task packages, and outputting the sorted plurality of coloring results to the pixel processing assembly line unit behind the geometric processing assembly line unit. The processor can improve the drawing efficiency.

The embodiment of the invention discloses a geometry processing method, a processor, equipment, a device, a storage medium and a product, which are applied to a primitive distribution module in a graphics processor, and the graphics processor further comprises a first pipeline and at least two second pipelines. The method comprises the following steps: acquiring a to-be-processed primitive output by a first pipeline and an accumulated processing vertex number of a shader in each second pipeline; each second pipeline comprises a curved surface subdivision unit and a shader, and the shader is used for processing a vertex after the curved surface subdivision unit performs curved surface subdivision on the to-be-processed primitive; determining the second pipeline meeting a preset load balancing condition from the at least two second pipelines as a target second pipeline according to the accumulated processing vertex number of the shader in each second pipeline; and distributing the to-be-processed primitives to the target second pipeline to indicate the target second pipeline to process the to-be-processed primitives. Through the method, the geometric processing performance of the graphics processor can be improved.

The application relates to the technical field of CAE preprocessing and cloud cooperation, and discloses a lightweight CAE geometry engine and a cloud real-time cooperation method and system. A cloud server acquires an original CAE geometry model, performs topological simplification and data compression on the original CAE geometry model, and generates a lightweight geometry data file containing multiple resolution levels; the cloud server pushes the received difference data packet to other online cooperation terminals; the other cooperation terminals parse the unique version number carried by the difference data packet through a locally loaded WebAssembly geometry engine module, and perform operation replay updating on the local geometry model according to the differential data contained in the difference data packet. According to the scheme, the original CAE model data volume is reduced by 90%-95%, the WebAssembly engine realizes a 100,000-face model rendering frame rate of 30-60 fps, and the operation response delay is less than or equal to 100 ms, thereby breaking through the performance bottleneck of browser-side geometry processing.

The invention discloses an LBM fluid design optimization method based on curvature adaptive voxel mapping and turbulence correction. The method comprises the following steps: step 1, constructing a system; 2, carrying out initial geometric processing; step 3, generating a curvature self-adaptive voxel; 4, turbulence correction LBM is solved; 5, closed-loop optimization design is carried out; according to the method, simulation is directly carried out on the voxel structure, so that a tedious grid division step is omitted, and the modeling and simulation process integration level is improved. Modeling, simulation and optimization are completed in one platform, a data closed loop is opened, and the design iteration efficiency is remarkably improved. The lattice Boltzmann algorithm accelerated by the GPU is adopted, rapid calculation of million-level voxels is supported, and the simulation time is shortened. By means of the curvature self-adaptive grid technology, the number of invalid calculation units is reduced by 30%-50%. For example, in NASA centrifugal pump simulation (2 million voxel scene), a traditional standard LBM method needs the calculated amount of 1580,000 core hours, while the method only needs 620,000 core hours, and the speed-up ratio reaches 2.55 times.

This disclosure provides a cross-platform parametric design method, apparatus, device, medium, and program, relating to the field of computer technology. The method includes: acquiring parametric design data from a first application software, the parametric design data including a geometric model file generated by the first application software and a corresponding parameter configuration file; inputting the parametric design data into a pre-built two-layer processing framework consisting of a geometry processing layer based on an OCCT geometric kernel and a scene description layer based on a USD format, used to map parameters in the parametric design data to geometric entities and encapsulate them into USD assets containing parametric feature information; outputting the USD assets to a second application software, enabling the second application software to modify parameters based on the parametric feature information in the USD assets, and triggering the two-layer processing framework to perform geometric reconstruction and synchronization of the modified parameters. This disclosure realizes cross-platform application of parametric design data and improves parametric design efficiency.

The present application relates to a kind of linear array swing scan type optical satellite on-orbit geometric calibration method based on equivalent surface array, comprising the following steps: step 1, by image matching or artificial measurement method, from high-precision digital orthophoto map and digital elevation model, obtain the ground control point on the single pendulum satellite image;Step 2, according to the geometric relationship between the rotating scanning mirror, motion compensation mirror and linear array CCD in satellite imager and its imaging process, construct linear array swing scan type optical satellite geometric calibration model based on equivalent surface array;Step 3, using ground control point, solve linear array swing scan type optical satellite geometric calibration parameter.The present application can realize linear array swing scan type optical satellite high-precision on-orbit geometric calibration, thereby providing support for linear array swing scan type optical satellite image high-precision geometric processing.

This invention provides a city-level 3D data update method and related equipment based on a digital twin visualization engine, comprising: drawing the 3D data region to be updated in a virtual city 3D space using a digital twin visualization engine; transforming the 3D data region between different coordinate systems to align the spatial positions of the 3D tile data and the base plate data; performing geometric processing on the nodes of the 3D tile data to reorganize the geometric data within the nodes; updating the data of all relevant nodes in a specified LOD level based on the update operation of the 3D data region; after completing the data update processing at the specified LOD level, performing layer-by-layer analysis and full-range data updates on other LOD levels; and storing the updated 3D tile data in an object repository and loading it into the application. This invention enables rapid and flexible local updates on a 3D base plate.

The application provides a graphics processing system, including at least two enabled graphics processing cores, and each graphics processing core includes a vertex splitting module, a vertex processing pipeline module, a primitive processing pipeline module and a pixel processing pipeline module. The vertex splitting module of a target graphics processing core is configured to determine a primitive packet to be processed by the target graphics processing core from vertex index data; the vertex processing pipeline module is configured to perform shading processing on vertices corresponding to indexes in the primitive packet to obtain a shading processing result; the primitive processing pipeline module is configured to obtain primitive composition information and perform geometric processing on the shading processing result based on the primitive composition information to obtain a geometric processing result; and the pixel processing pipeline module is configured to process the geometric processing result to obtain a visualized graphics.

A graphics processor executes a graphics processing pipeline generating an output. The pipeline comprises geometry processing stage(s) and a rendering stage rendering an output. The geometry stage(s)

This invention relates to a seamless dynamic loading method for electronic nautical charts, belonging to the field of electronic nautical chart display technology. During system initialization, an R-tree spatial index is constructed to quickly retrieve and filter the set of objects to be displayed based on the current viewport range and scale. The objects are divided into base layers and enhancement layers, assigned different rendering priorities, and spatially sorted to generate an ordered list of objects to be rendered. A thread pool with four worker threads is created, and the rendering process is decomposed into three stages: geometry processing, symbolization, and image synthesis, which are executed in parallel. A display list caching and double-buffering mechanism are employed to ensure smooth playback. Frame rate and memory usage are monitored in real time, and two levels of anomaly thresholds are established to dynamically trigger a degradation strategy from pausing enhancement layers to simplifying base layers, and automatic rollback occurs after resource recovery. This invention effectively solves the problems of lag and memory efficiency when loading massive vector data, significantly improving the smoothness and stability of electronic nautical chart display.

The present disclosure provides systems, devices, apparatuses, and methods, including computer programs encoded on storage media, for variable rate tessellation. A graphics processor can receive data for geometry processing of a plurality of tiles in a draw call. The graphics processor can reduce a tessellation factor for each tile of the plurality of tiles based on a characteristic of each tile of the plurality of tiles. The reduced tessellation factor can correspond to a TRF. The characteristic can correspond to a shading rate or a number of visible pixels. The graphics processor can apply the TRF for each tile of the plurality of tiles. The graphics processor can render each tile of the plurality of tiles based on the applied TRF for each tile of the plurality of tiles.

This invention discloses a three-dimensional embedded discrete crack network geometric processing method applicable to cracks with arbitrary tilt angles, including: reading crack data for each crack; calculating the coordinates of the four vertices of the crack; calculating crack segments with tilt angles not equal to 90° and equal to 90° respectively; this invention solves the problem of difficult geometric processing of cracks with arbitrary tilt angles in three-dimensional EDFM models.

Streaming video content comprising a plurality of rendered image frames to a client device via a server, the server comprising a geometry processing unit configured to perform a geometry pass on a sce

The invention provides a data processing method, a graphics processor, equipment, a storage medium and a program product. The method comprises the steps that corresponding primitive group data are processed through a geometric processing pipeline, a primitive group processing result is obtained, and the primitive group data are part of data in a geometric data stream; determining coverage block information corresponding to the primitive group processing result through a management module, and applying for a primitive storage space for the primitive group processing result based on the coverage block information; the coverage block information is used for representing the information of the primitive coverage blocks in the primitive group processing result; and partitioning the primitive group processing result through a partitioning device, and storing the partitioned primitive group processing result in a primitive storage space corresponding to the primitive group processing result. By adopting the technical scheme provided by the invention, unnecessary waste of storage resources can be avoided.

This application provides a palm contour extraction method performed by a computer device. The method includes: obtaining bone point information respectively corresponding to palm bone points in a target palm image, the bone point information including bone point positions and bone point types; matching the palm bone points based on the bone point positions and the bone point types, to obtain a plurality of palm bone point sets, each palm bone point set having a corresponding geometry processing type for a corresponding set of palm bone points in the target palm image; determining a plurality of palm contour points from the plurality of palm bone point sets based on their respective geometry processing type; and generating a palm contour corresponding to the target palm image based on the plurality of palm contour points.