Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

536 results about "Real-time rendering" patented technology

Real-time rendering is one of the interactive areas of computer graphics, it means creating synthetic images fast enough on the computer so that the viewer can interact with a virtual environment. The most common place to find real-time rendering is in video games. The rate at which images are displayed is measured in frames per second or Hertz. The frame rate is the measurement of how quickly an imaging device produces unique consecutive images.

Three-dimensional scene reconstruction method and device based on large model geometric prior, and medium

The invention discloses a three-dimensional scene reconstruction method and device based on large model geometric prior, and a medium, and aims to solve the problems that a conventional 3DGS is liable to have artifacts and detail loss in geometric discontinuity, data redundancy and illumination variation scenes, and predicts a dense depth map and a normal map from a monocular image by using a pre-trained large model. The position and form of the Gaussian kernel are constrained as additional geometric priori; a primitive adjustment strategy based on kernel density estimation is introduced in the training stage, small Gaussian primitives with similar structures and adjacent spaces are combined into a large Gaussian primitive, the rendering quality is kept, redundancy is reduced, and the volume of the model is reduced; an exposure coefficient is adaptively estimated for each input image, an exposure compensation image loss function is constructed, and floating artifacts caused by illumination differences at shooting moments are eliminated. Experiments show that compared with the prior art, the method improves the three-dimensional reconstruction precision and real-time rendering quality of complex illumination and less-texture areas in a public data set and an unmanned aerial vehicle aerial photography scene.
Owner:NARI INFORMATION & COMM TECH

High-resolution three-dimensional reconstruction method of fusion diffusion model

The invention discloses a high-resolution three-dimensional reconstruction method of a fusion diffusion model, which belongs to the technical field of image data processing, and comprises the following steps: constructing an original data set D; constructing an enhanced training set; constructing a three-dimensional reconstruction network which comprises a text encoder, a renderer, a VAE encoder, a conditional diffusion model, a VAE decoder and an MVS module; training and fine-tuning the conditional diffusion model in three stages to obtain a three-dimensional reconstruction model, acquiring an image sequence and a text instruction of a scene to be reconstructed, and performing reconstruction by using the three-dimensional reconstruction model. According to the method, highly consistent geometric and color reduction can be kept under the multi-view condition, and splicing artifacts are remarkably reduced. Through semantic guidance optimization, texture details and structural consistency of the reconstruction model are greatly improved. Conditional diffusion sampling enables the model to accurately restore local details in a complex scene, and the stability of real-time rendering is improved.
Owner:SHENZHEN SENSING DATA TECH CO LTD +1

Virtual actor based on 4D Gaussian splashing and XR and on-site immersive real-time presentation system and method thereof

The invention belongs to the technical field of augmented reality (XR) and computer vision crossing, relates to fusion application in immersive digital performance, and provides a virtual actor reconstruction and immersive presentation system based on 4D Gaussian splash modeling and XR space positioning. The system comprises a set of spherical multi-camera-position high-synchronization camera shooting matrix used for capturing dynamic images of actors; performing dynamic modeling on the multi-angle image through a 4D Gaussian splashing technology, and outputting a virtual actor point cloud model which can be used by XR equipment; vPS visual positioning and an SLAM tracking module are combined, and precise mapping positioning of a performance space is achieved in AR / MR equipment. The method supports the immersive watching of the actor image at the audience end at a 360-degree free visual angle, and realizes the natural presentation of the virtual actor without dead angles and wearing in cooperation with shielding judgment and a real-time rendering engine. The system is widely applicable to on-site entertainment scenes such as immersive theaters, text travel performances, brand activities, concerts and television programs.
Owner:SHANGHAI SHICHEN CULTURAL COMMUNICATION CO LTD

Gaussian model construction method and device, program product and storage medium

The invention discloses a Gaussian model construction method and device, a program product and a storage medium, and relates to the technical field of computer vision. The method comprises the following steps: acquiring multi-view images, and obtaining a three-dimensional Gaussian element corresponding to each multi-view image; establishing a hierarchical data structure; selecting a training view angle to obtain a trained three-dimensional Gaussian element; calculating a stability score of each trained three-dimensional Gaussian element, and performing hierarchical construction operation according to each stability score to obtain a plurality of space clusters; calculating a representative parent cluster; performing rasterization processing to obtain a rendering result; calculating rendering loss, and adding the representative parent cluster into the hierarchical data structure to obtain a target hierarchical data structure; and repeatedly executing the training operation and the hierarchical construction operation until the rendering loss is lower than a preset loss threshold value, and outputting a three-dimensional Gaussian scene model containing the target hierarchical data structure. By implementing the technical scheme provided by the invention, the performance pressure faced by real-time rendering can be reduced.
Owner:SHENZHEN SAIER INTELLIGENT CONTROL TECH CO LTD

Real-time rendering and interaction method for immersive virtual reality scene

The invention relates to the technical field of computers, and discloses a real-time rendering and interaction method and system for an immersive virtual reality scene. The method comprises the following steps: fusing tuner inertial data and eyeball tracking data, and constructing a prospective state prediction model; generating a predictive focus field in combination with scene visual saliency; synthesizing an anisotropic temporal-spatial resolution graph according to the predicted head angular velocity; gPU variable-rate coloring is driven to realize non-uniform rendering; and re-projection or dynamic fuzzy correction is executed in a self-adaptive manner according to the attitude prediction error before display. According to the technical scheme, the perception delay and the rendering load are remarkably reduced, and the frame rate stability and the visual immersion in a high-dynamic scene are improved.
Owner:CHENGDU TECHNICIAN COLLEGE (CHENGDU VOCATIONAL & TECH COLLEGE OF IND & TRADE CHENGDU ADVANCED TECH SCHOOL CHENGDU RAILWAY ENG SCHOOL)

Augmented reality intelligent navigation and operation quantitative evaluation method and system in operating room

The invention discloses an augmented reality intelligent navigation and operation quantitative evaluation method and system in an operating room, and the method comprises the steps: collecting multispectral image data and depth point cloud data of an operation region in the operating room in real time, and generating a multidimensional perception data set; performing feature extraction and spatial registration on the multi-dimensional perception data set, and decomposing the dynamic three-dimensional augmented reality model into an anatomical structure feature layer and an instrument interaction feature layer; performing dynamic matching and real-time rendering on the anatomical structure feature layer and the instrument interaction feature layer based on a digital twinning technology to generate augmented reality navigation information and an operation guidance scheme; and performing multi-dimensional quantitative analysis on the surgical operation process according to the augmented reality navigation information and the operation guidance scheme, and outputting a quantitative evaluation result. By utilizing the embodiment of the invention, augmented reality navigation guidance which is synchronous with a real operation scene in real time can be provided, meanwhile, accurate quantitative evaluation is carried out on the operation operation, and the accuracy, the safety and the trainability of the operation are improved.
Owner:HANGZHOU NORMAL UNIVERSITY

Volume cloud rendering method and system based on three-dimensional Gaussian splashing

The invention discloses a volume cloud rendering method and system based on three-dimensional Gaussian splash, and the method comprises the steps: carrying out the feature matching and structure reconstruction of a volume cloud image through an SfM algorithm, obtaining a sparse point cloud in a scene, and representing the sparse point cloud as an anisotropic Gaussian ellipsoid; decomposing the illumination transmission process of the volume cloud into two parts of forward single scattering and internal multiple scattering based on a radiation transmission equation to obtain an illumination modeling formula embedded volume cloud rendering process; determining the contribution of each three-dimensional Gaussian ellipsoid to a rendering result according to the opacity index of the three-dimensional Gaussian ellipsoid, and dynamically cutting the low-contribution three-dimensional Gaussian ellipsoid by adopting a delay deletion strategy to reduce redundancy; a comprehensive loss function is constructed, so that the three-dimensional Gaussian model is focused on the volume cloud region and the structure detail reduction capability is enhanced; and outputting the optimized volume cloud rendering result and the three-dimensional Gaussian model. According to the method, the volume cloud rendering efficiency and quality are effectively improved on the premise of ensuring real-time rendering.
Owner:NANJING UNIV OF INFORMATION SCI & TECH

Dynamic scene incremental reconstruction and rendering method based on 3DGS

The invention discloses a dynamic scene incremental reconstruction and rendering method based on 3DGS, and belongs to the field of specific computer models, and the method comprises the steps: constructing a 3DGS model at an initial moment based on an original image set; obtaining any visual angle image at the moment t in the dynamic scene, and determining a first updating area through semantic segmentation and target recognition; generating an increment updating region based on the luminosity error, the local similarity and the global semantic feature; generating a second update region, modeling in the second update region, and minimizing region reconstruction errors to generate an optimized Gaussian point set; and fusing and optimizing the real-time model at the previous moment to obtain a real-time model Gt at the moment t for real-time rendering. According to the method, geometric and texture information of a scene can be effectively coded, accurate detection and local increment updating of a dynamic region are supported, Gaussian point parameters are optimized to improve the continuity and visual quality of a model, low-delay real-time rendering is realized, and the efficiency and quality of three-dimensional scene processing in a dynamic environment are effectively improved.
Owner:SHENZHEN SENSING DATA TECH CO LTD

Indoor three-dimensional image intelligent rendering method based on image processing

The invention relates to the technical field of image processing, and provides an indoor three-dimensional image intelligent rendering method based on image processing. Comprising the following steps of indoor multi-view image acquisition, image preprocessing, intelligent analysis of indoor scene elements, construction of an indoor three-dimensional initial model with attributes, intelligent generation of rendering parameters, adaptive LOD real-time rendering and intelligent interaction optimization. According to the intelligent interaction optimization system, through deep fusion of natural language processing, user preference learning and real-time rendering technologies, a set of efficient, visual and personalized virtual scene rendering interaction process is constructed. According to the method, the problems that traditional graphic software is complex in operation, high in learning cost and low in debugging efficiency are solved, and the user satisfaction and creation efficiency are remarkably improved through an intelligent recommendation and rapid iteration mechanism.
Owner:贵州轻工职业大学 +1

Self-adaptive multi-view track roaming optimization method and system based on Cesium

The invention provides an adaptive multi-view track roaming optimization method based on Cesium, and the method comprises the steps: obtaining an original path point, and carrying out the processing of the original path point, and generating a smooth path; dynamically adjusting the time rate of the smooth path movement; dynamically adjusting the number of interpolation points of the smooth path; loading the dynamically adjusted path, and binding with the path through a dual-mode view angle; and rendering the path in real time, and interacting with a user. According to the method, a Catmull-Rom spline interpolation and inflection point optimization method is adopted, so that turning is smoother; the terrain height is dynamically sampled, terrain adaptation is accurate, and the model is prevented from being suspended or falling into the ground; according to the invention, first person / third person switching is supported, and flexible visual angle control is realized; the speed calculation based on the path length ensures that the motion rhythm is natural.
Owner:武汉智博创享科技股份有限公司

Systems and methods for rendering AI generated videos in real time

Methods, systems, and computer readable media for rendering context-aware and interactive artificial intelligence-generated videos in real time. A talking face (“TF”) model may traverse from a first node to a second node of a state graph via an edge based on a TF instruction generated by an interaction model. The TF model may retrieve a transition video associated with the edge and a pre-computed video template associated with the second node from one or more TF databases. The pre-computed video template may include a plurality of masked video frames and a plurality of pre-computed mouth positions for each masked video frame. The TF model may inpaint a pre-computed mouth position into a masked region of each masked video frame to form a video frame stream. The interaction model may generate a video from the transition video and the video frame stream and present the video on a user device.
Owner:LAGENA INC

Ship network security digital twin full life cycle maintenance and monitoring method

The invention relates to a ship network security digital twinning full life cycle maintenance and monitoring method, which comprises the following steps: step 1, constructing a digital twinning 3D virtual model of a ship network, the 3D virtual model is based on an actual network topology structure of a ship, and comprises all network nodes including a switch, a router, a sensor and a control system; and real-time rendering is carried out on local equipment or a cloud platform. According to the method, the real-time mapping of the high-fidelity 3D virtual model and the physical network is constructed, the three-dimensional and visual monitoring of the ship network state is realized, the cognitive efficiency of operation and maintenance personnel on the complex network topology is greatly improved, the cloud-side collaborative intelligent analysis architecture is adopted, and the real-time monitoring of the ship network state is realized. According to the method, the local real-time threat detection capability in an unstable network environment is ensured, the defense level of the system is continuously improved through cloud deep learning and model optimization, multi-source heterogeneous data acquisition and intelligent analysis are combined, and hidden attacks and abnormal behaviors which are difficult to find by a traditional method can be accurately recognized.
Owner:NANTONG BIAOYI TESTING SERVICE CO LTD

AI-based low-code visual component dynamic generation method and system

The invention relates to the field of computer software, and provides an AI-based low-code visual component dynamic generation method and system. The method comprises the following steps: receiving a component demand description input by a user, and converting the component demand description into structured cue word data to obtain an initial cue word sequence; retrieving matched template data and grammatical rule data from a component knowledge base according to the initial cue word sequence, and fusing the template data, the grammatical rule data and the initial cue word sequence to obtain an enhanced cue word sequence; performing semantic analysis and code generation processing on the enhanced cue word sequence through a large language model to obtain a component source code; and performing real-time rendering processing on the component source code through a component rendering engine, and generating an interactive component instance in a preview interface to obtain reusable component resources. According to the method, the code quality consistency is ensured, and the development efficiency is improved.
Owner:CHINA DATACOM CORP LTD

Generative AI model real-time rendering engine construction method and related equipment thereof

The invention discloses a generative AI model real-time rendering engine construction method and related equipment thereof, and relates to the technical field of man-machine interaction, and the method comprises the steps: obtaining multi-modal semantic information input by a user, and converting the multi-modal semantic information into a patent vector and a constraint parameter; constructing a lightweight generation model, and directly generating a renderable intermediate representation by adopting the lightweight generation model; constructing a rendering pipeline based on the generated intermediate representation, and converting the intermediate representation into a visual image; capturing user operation in real time, dynamically updating constraint conditions of a generated model, triggering increment generation, and optimizing system performance by adopting a model lightweight, hardware acceleration and hybrid rendering strategy; through the time filtering and space constraint technology, the generated content is consistent in time and space. According to the method, the problems of low generation speed and low rendering efficiency in the fusion process of the generative AI model and the real-time rendering engine are solved, and the efficiency and quality of visual image generation and rendering are improved.
Owner:SHANGHAI YINGZHONG INFORMATION TECH CO LTD

Fire scene spreading time sequence reconstruction method and system based on Doppler weather radar mountain fire echo

The invention relates to the technical field of forest fire monitoring and power grid safety prevention and control, and discloses a fire scene spreading time sequence reconstruction method based on Doppler weather radar mountain fire echoes, which comprises the following steps: acquiring original data of the Doppler weather radar mountain fire echoes and carrying out quality control processing to obtain radar echo data; performing automatic segmentation of a smoke plume area on radar echo data by adopting an optimized Otsu-Unet network model, and extracting a centroid coordinate of a mountain fire echo area; a Kalman filtering algorithm is used and combined with external three-dimensional wind field data to predict a future motion trend of centroid coordinates of a forest fire echo region so as to reconstruct a continuous fire scene spreading time sequence voxel sequence; performing 3DTiles slicing processing on the fire scene spreading time sequence voxel sequence, and performing real-time rendering display on a power grid monitoring platform by using a WebGL technology; and obtaining an external expansion boundary of fire scene spreading based on the fire scene spreading time sequence voxel sequence, and calculating the distance between the external expansion boundary and the power transmission line GIS data in real time. The fire prevention and control capability of the power transmission line of the power grid is improved.
Owner:STATE GRID SICHUAN ELECTRIC POWER CORP ELECTRIC POWER RES INST

Scene generation method and device based on multi-source GIS data fusion

The invention discloses a scene generation method and device based on multi-source GIS data fusion, and relates to the technical field of digital twinning and programmed generation. The method comprises the following steps: acquiring GIS data, preprocessing the GIS data, and storing the preprocessed GIS data in a geographic information resource library; a structured resource library is constructed, semantic parameters are added to the three-dimensional model in the structured resource library through the configuration file, and three-dimensional model resources with structured semantics are constructed; on the basis of the three-dimensional model resources with structured semantics and GIS data in a geographic information resource library, building and road generation and terrain processing are carried out in a programmed modeling engine through a configuration file, and scene data are generated; and importing the generated scene data into a real-time rendering engine, carrying out dynamic environment interaction and biocenosis simulation, and generating a city scene. The problems that in the prior art, an urban three-dimensional modeling method is low in efficiency and insufficient in environment interaction reality sense are solved.
Owner:TUDOU DATA (HANGZHOU) HOLDINGS CO LTD

Real-time interactive visualization system and method based on digital twinning

The invention relates to the technical field of digital twinning, in particular to a real-time interactive visualization system and method based on digital twinning, and the system comprises a data collection module which is used for configuring a multi-protocol adapter deployed on a physical equipment layer to collect the operation data of physical equipment, and transmitting the operation data of the physical equipment to an edge computing node. According to the method, the general data adapter is used for driving the three-dimensional rendering engine to execute real-time rendering based on physics, so that the virtual scene can dynamically reflect details such as illumination change and material aging of a physical entity, and high-fidelity visual feedback is provided. According to the method, a closed-loop control mechanism is established in combination with a multi-modal interaction framework, pure data monitoring is converted into operable bidirectional interaction, operation of a user on a visual interface can be converted into feedback instructions in real time to reversely adjust physical equipment, and the response efficiency of remote operation and maintenance is improved.
Owner:ZHEJIANG TIANNENG NEW ENERGY CO LTD

Three-dimensional voxel geometry collision detection method based on feature layering and multiple detection strategies

The invention discloses a three-dimensional voxel geometry collision detection method based on feature layering and multiple detection strategies, and relates to the technical field of computer graphics and game engines, the method comprises bit compression storage optimization, feature layering extraction and multiple collision detection, through the feature layering and multiple detection strategies, the unnecessary calculation amount is effectively reduced, and the detection efficiency is improved. The overall performance of the algorithm is improved, efficient memory compression is achieved while the detection precision is guaranteed, the requirement for computing resources is reduced, the technology can stably run in the resource-limited environment, unified collision detection processing of various geometries is supported, the universality and flexibility of the system are improved, and the system performance is improved. According to the method, integration and application in different application scenes are facilitated, the real-time rendering capability is optimized, the mobile terminal and the VR equipment are supported to run a complex physical simulation scene at a high frame rate, and the user experience and the interaction effect are improved.
Owner:Beijing Yidong Information Technology Co., Ltd.

Operation interaction method and system applied to camera image editing

The invention discloses an operation interaction method and system applied to camera image editing, and relates to the technical field of image processing, and the method comprises the steps: obtaining a voice semantic heat map, a pointing intensity map, a touch confidence map and a gazing confidence map based on a multi-modal interaction data packet, and calculating an image feature matrix at the same time; fusing into a multi-modal evidence graph through a normalized scale; performing semantic segmentation according to the image feature matrix to obtain a semantic segmentation first draft and a pixel-by-pixel category confidence coefficient, and performing position correlation weighting on the pixel-by-pixel category confidence coefficient by taking the multi-modal evidence graph as a confidence coefficient modulation factor to generate a candidate object mask sequence; and performing highlight display on the candidate object mask sequence, and performing conflict resolution and priority rearrangement in combination with the multi-mode evidence graph to generate a target object mask. According to the method, deep fusion of the interaction intention and image segmentation is realized, the precision and consistency of candidate region detection are improved, and the stability of real-time rendering and the reliability of an editing result are improved.
Owner:SHENZHEN XUJING DIGITAL TECH CO LTD

First-view-angle drilling method and device based on memory enhancement and storage medium

The invention relates to the technical field of robot perception and data generation technologies, in particular to a first-view-angle drilling method and device based on memory enhancement and a storage medium, and the method comprises the steps: extracting a plurality of target frames from a historical video stream stored in a space intelligent machine, obtaining a plurality of memory elements based on the plurality of target frames, performing three-dimensional reconstruction on each target frame, constructing a target world model, planning a first visual angle track of the target robot in the target world model, performing imaging simulation on the target robot, performing real-time rendering on a first visual angle video of the target robot, and performing real-time rendering on a second visual angle video of the target robot based on the same time axis and action script as the first visual angle video. A third-person video corresponding to the space intelligent machine is generated, and a drilling result is output; according to the method, the long-term memory data of the space intelligent machine is ingeniously used, high-quality drilling data can be quickly generated, the reliability of the first-view video is improved, and a reliable basis is provided for training and testing of a robot algorithm.
Owner:BEIJING QIDAISONG TECH CO LTD

AI digital human real-time rendering method based on GPU acceleration

The invention discloses an AI digital human real-time rendering method based on GPU acceleration, and relates to the technical field of digital human rendering, and the method comprises the steps: S1, constructing a multi-GPU hardware feature and load monitoring module, and collecting hardware feature parameters and current load states of each GPU participating in collaborative rendering in real time; according to the method, by constructing the multi-GPU hardware feature and load monitoring module and combining a dynamic task allocation algorithm, dynamic allocation of the rendering sub-tasks to the optimal GPU is achieved, the problems of GPU performance bottleneck and resource idleness caused by traditional fixed task allocation are solved, the multi-GPU collaborative rendering efficiency is improved, and the multi-GPU collaborative rendering efficiency is improved. A scene complexity analysis module and a self-adaptive resource allocation algorithm are built, the proportion of GPU resources between an AI driving module and a rendering module is dynamically adjusted according to scene complexity, the AI digital human interaction naturalness is improved in a simple scene, the rendering frame rate and the picture quality are guaranteed in a complex scene, and the method is suitable for being used in a large-scale scene. And finally, dual optimization of rendering efficiency and picture quality in AI digital human real-time rendering is realized.
Owner:GUANGZHOU PERANG IND CHAIN DEVELOPMENT CO LTD

Hierarchical occlusion perception grid infinitesimal streaming and adaptive rendering method

The invention relates to a hierarchical occlusion perception grid infinitesimal streaming transmission and adaptive rendering method, which comprises the following steps of: S1, decomposing a model into grid infinitesimal, recursively constructing a bounding volume hierarchical tree BVH from bottom to top by taking the grid infinitesimal as a leaf node, and setting a semantic error and a geometric error for each sub-node cluster; s2, acquiring camera parameters of a current frame, comparing a total screen space error with an error threshold value, if the error is smaller than the threshold value, stopping traversing, and adding the cluster node into a to-be-rendered list of the current frame; and S3, if the grid infinitesimal corresponding to the cluster node in the to-be-rendered list is not loaded to the GPU memory, sending a loading request to an asynchronous streaming manager, asynchronously loading the corresponding grid infinitesimal from the memory, and rendering a father node of the cluster node. Compared with the prior art, the method has the advantages that large-scale and high-precision model data can be rendered on the lightweight XR all-in-one machine in real time, and the like.
Owner:SHANGHAI JIAOTONG UNIV

Multi-scene fusion automatic driving analog simulation test method and system

The invention belongs to the field of automatic driving, and particularly relates to a multi-scene fusion automatic driving analog simulation test method and system, and the method comprises the steps: obtaining multi-source heterogeneous driving data, carrying out the preprocessing and fusion of the multi-source heterogeneous driving data, and obtaining standardized scene data; based on the standardized scene data, constructing a basic simulation scene by adopting a photo-level real-time rendering technology, and optimizing and constructing the basic simulation scene into a three-dimensional scene model by adopting a 3D Gaussian splashing technology; based on a preset scene generation rule and through a 4D space-time modeling algorithm, performing expansion and variation on the three-dimensional scene model, and automatically generating a multi-dimensional test scene set; executing a simulation test corresponding to the multi-dimensional test scene set, and collecting test result data of the automatic driving system; and establishing a scene optimization and algorithm iteration closed-loop mechanism based on the test result data, and dynamically optimizing the multi-dimensional test scene set and the automatic driving system algorithm.
Owner:INST OF PHYSICS HENAN ACAD OF SCI +1

Code stream real-time rendering method and device, electronic equipment and readable storage medium

The invention provides a code stream real-time rendering method and device, electronic equipment and a readable storage medium, and relates to the technical field of artificial intelligence such as large language models, hypertext markup languages, streaming processing and webpage generation. The method comprises the steps of obtaining a code stream of a hypertext markup language continuously output by a large model and used for generating a target webpage; performing streaming processing on the continuously acquired code stream according to the following preset streaming analysis mechanism: in response to the detected complete script tag, extracting the script to be processed corresponding to the complete script tag to a preset script management system; in response to the detected frame tag, processing and displaying the content of the frame tag in a sub-page created for the frame tag; the real-time streaming result is presented as a real-time web page rendering result corresponding to the portion of code received from the code stream. By applying the method, the rendering efficiency of obtaining the target webpage based on the code can be remarkably improved, and the waiting time of a user is shortened.
Owner:BEIJING BAIDU NETCOM SCI & TECH CO LTD

Image super-resolution edge reconstruction method and system based on morphology and coverage rate perception

The invention discloses an image super-resolution edge reconstruction method based on morphology and coverage rate perception. The method comprises the following steps: dividing an image into an edge region and a non-edge region based on depth and brightness information; anti-aliasing edge detail recovery is realized through coverage rate perceived depth mode classification and a table look-up filter; generating direction features by using the brightness gradient and keeping details through a table look-up filter; and combining the reconstruction results of the current frame and the historical frame to ensure the image stability in a dynamic scene. The invention also provides an image super-resolution edge reconstruction system. According to the method provided by the invention, the quality of an object edge and a newly appearing pixel region can be remarkably improved, sawtooth artifacts are effectively inhibited, and relatively high time stability is kept in a dynamic scene, so that the requirements of real-time rendering and visual enhancement application are met.
Owner:HANGZHOU GONGSHU DISTRICT HOLOGRAPHIC INTELLIGENT TECHNOLOGY RESEARCH INSTITUTE

Grid data processing method, system and equipment of three-dimensional virtual model and medium

The invention provides a grid data processing method, system and device of a three-dimensional virtual model and a medium, and belongs to the technical field of three-dimensional virtual model processing, and the method specifically comprises the following steps: receiving original grid data; performing feature extraction and probability distribution on the vertex set; constructing an expansion graph through a k-nearest neighbor algorithm, calculating an edge connection probability, and multiplying the original adjacency matrix by the attention weight matrix to generate a simplified adjacency matrix; and performing feature coding and probability classification on the candidate triangle set, filtering and correcting non-manifold edges to obtain a simplified triangle set, and transmitting the simplified triangle set to target equipment. According to the invention, the lightweight processing of the original grid data is realized. On the premise that key geometric and topological characteristics of the model are not affected, the operation efficiency of the model on the target equipment is improved, the loading time is shortened, the display fluency is improved, and powerful support is provided for application of the three-dimensional model in scenes with high model response speed requirements such as virtual assembly, analogue simulation and real-time rendering.
Owner:SHANGHAI UNIV

Digital human real-time rendering method and device and computer equipment

The invention provides a digital human real-time rendering method and device and computer equipment, and relates to the technical field of image processing, in particular to the fields of real-time rendering, digital human rendering and the like, and the implementation scheme is as follows: collecting a plurality of real-time computing power parameters of a terminal; normalizing the plurality of real-time computing power parameters into computing power index vectors; determining whether the computing power change of the terminal exceeds a preset change threshold according to the computing power index vector; when the computing power change of the terminal exceeds a preset change threshold value, inputting the computing power index vector into a trained reinforcement learning model to determine a target rendering mode of the digital human; and switching the rendering mode of the digital human from the current rendering mode to the target rendering mode. Therefore, a universal rendering scheme for evaluating the available computing power in real time and dynamically adjusting the digital human rendering level can be provided so as to meet the high-frame-rate, low-delay and extensible rendering requirements.
Owner:VASTAI TECH (SHANGHAI) INC

Three-dimensional science popularization animation generation method and system based on AIGC technology

The invention provides a three-dimensional science popularization animation generation method and system based on an AIGC technology, and relates to the technical field of animation generation. The method comprises the following steps: firstly, fusing structured knowledge such as an anatomy term library, a diagnosis and treatment process guide and a drug specification with electronic medical records and CT / MRI volume data, and generating a split script and a medical term list through a large language model; then reconstructing an organ or focus grid by using a script-image combined driven text-three-dimensional diffusion model, and executing anatomical consistency correction according to the medical knowledge graph; automatically arranging a time axis, a camera track and a skeleton action, and synchronously synthesizing multilingual parastyle subtitles; and finally, frame-level rendering and compression packaging are completed in a real-time rendering engine, and efficient, professional and iterable medical animation generation is realized by means of an expert feedback closed-loop fine tuning model.
Owner:FIRST HOSPITAL AFFILIATED TO GENERAL HOSPITAL OF PLA

Interactive three-dimensional rendering system and method

The invention relates to an interactive three-dimensional rendering system and method, and the system is characterized in that a three-dimensional rendering server carries out the signaling exchange according to a connection request, builds a webpage real-time communication channel, compresses a rendered image frame into a video stream through the webpage real-time communication channel, and transmits the video stream to a client for display; when the client detects an interaction operation of a user, the generated instruction interaction data is transmitted to the three-dimensional rendering server through a webpage real-time communication channel; the three-dimensional rendering server applies the instruction interaction data to the rendering process of the image frame according to the three-dimensional map service unit and the preset instruction information, so that the client updates the displayed video stream; unified processing of video stream transmission and instruction interaction is realized by establishing a standardized webpage real-time communication channel, different map engine interfaces are compatible by adopting a preset instruction protocol specification, the system integration complexity is reduced while the real-time rendering performance is ensured, and the method has the advantages of improving cross-platform interaction compatibility and reducing instruction analysis delay.
Owner:WUHAN SURVEYING GEOTECHN RES INST OF MCC +1

Partitioning and hierarchical caching-based track point visual rendering method adaptive to localization

The invention discloses a localization-adaptive track point visual rendering method based on partitioning and hierarchical caching, and the method comprises the steps: S1, inputting a track data stream, carrying out the reading according to the source type of the data stream, and carrying out the data partitioning and LOD processing of the track point data; s2, performing data analysis and rendering on the data; s3, carrying out batch processing on GPU vertexes, according to the state of the circular buffer, if the vertexes are writable, incrementally writing vertex data, and if Wrap is needed, carrying out loopback writing and updating a pointer; and S4, finally, the descriptors and the styles are updated, rendering increment drawing is carried out on the track points, and visual display is carried out. The method supports real-time rendering and playback of ten-million-level track points, has visual and instantiated rendering of window dynamic loading, space-time partitioning, hierarchical caching and WebWorker decoupling calculation, and improves the space-time data rendering capability of the domestic autonomous controllable field by ten thousand times; and the user experience is greatly improved by a non-perceptual interaction and transition smoothing algorithm.
Owner:NANJING HONGSONG INFORMATION TECH CO LTD