23 results about "Skeletal animation" patented technology

The application provides a digital human head hair lighting data generation method and a digital human head hair rendering method, relates to the technical field of digital humans, and generates hair shape data capable of accurately controlling the shape of hair based on skeleton animation data through the calculation of a cloud server, and then directly generates hair lighting data in combination with environment data. The core of the method is that the inference ability of deep learning replaces traditional physical simulation and ray tracing calculation, successfully transfers the high complexity of the lighting calculation task to the cloud server, can realize high-fidelity real-time rendering of digital human hair in a dynamic motion and dynamic lighting environment without relying on high-performance terminal hardware, and solves the problems that the lighting map in the prior art cannot adapt to dynamic changes and the real-time ray tracing computing power is too high.

This invention discloses a rendering method, system, and storage medium for skeletal animation. The method includes: acquiring animation control parameters for each model instance, the animation control parameters including an animation identifier, the current playback frame, and a world transformation matrix, but excluding the skeletal transformation matrix; writing the animation control parameters of each model instance into an instance data buffer and sending a single-draw instruction to the GPU, the instance data buffer being located in GPU video memory and configured to be writable by the CPU and readable by the GPU; the GPU responding to the single-draw instruction by sampling the skeletal transformation matrix from a pre-stored animation matrix texture based on the animation control parameters in the instance data buffer, and performing parallel skinning calculations on each model instance based on the sampled skeletal transformation matrix. This method frees the CPU from skeletal matrix calculations, avoiding CPU rendering thread overload and preventing severe frame rate fluctuations and frame drops.

The invention provides a skeletal animation generation method, system and device, electronic equipment, a computer readable storage medium and a computer program product. The skeletal animation generation method comprises the steps that hand data, collected by first collection equipment, of a biological object and body data, collected by second collection equipment, of the biological object are obtained; generating a first hand skeletal animation of the biological object based on the hand data, and generating a body skeletal animation of the biological object based on the body data; fusing the first hand skeletal animation with the body skeletal animation to obtain a target body skeletal animation of the biological object; wherein the hand skeletal animation in the target body skeletal animation is obtained based on the generated hand skeletal animation. In this way, the accuracy and meticulous performance of the hand skeleton animation can be improved when the body skeleton animation is generated.

The invention relates to an interaction method and system based on a Web front end and electronic equipment, and the method comprises the steps: calling a terminal camera through a browser, obtaining a video stream of a user, and processing the video stream at the front end of the browser to extract human body key points; mapping the human body key points into skeleton animation parameters of the virtual image through a hierarchical action mapping engine; calculating a relative pose of the virtual article and the virtual image according to a preset attribute and a skeleton animation parameter of the virtual article; and in a browser environment, according to the relative pose, rendering and displaying an interaction picture of the virtual article and the virtual image. The problems of high hardware dependency, poor cross-platform compatibility, simple interaction link and serious delay and distortion in the prior art are solved. Special hardware is not needed, the use threshold of a user is lowered, and cross-platform compatibility is achieved based on a Web technology stack.

The embodiment of the invention provides a skeletal animation generation method and system. The skeletal animation generation method comprises the steps of obtaining a virtual skeleton of a virtual object and a grid model corresponding to the virtual skeleton; based on the orientation data of the virtual skeleton, mapping on the grid model to obtain a positioning point corresponding to the virtual skeleton; playing the grid model animation, and obtaining a first type of driving data and a second type of driving data of the positioning point; and controlling the virtual skeleton to rotate based on the first type of driving data, and controlling the virtual skeleton to move based on the second type of driving data to obtain a virtual skeleton animation. On the premise of not depending on manual binding and not losing physical details of a flexible object, automatic lossless mapping from a physical model vertex animation to an engine skeleton animation is achieved, the labor requirement for work is reduced, the skeleton animation manufacturing efficiency and quality are improved, and the method can be widely applied to the field of digital culture product manufacturing software.

The invention discloses a digital human real-time generation method and system fusing a layered light transmission model, and relates to the technical field of digital human modeling and real-time rendering. The method comprises the following steps: collecting optical parameters of each layer of skin, constructing a layered skin light transmission model and a radiation flux equation of each layer, carrying out layered adaptive photon mapping sampling, fusing radiation transmission results of each layer through a neural network accelerator, generating a skin material containing a dynamic reflectivity field, and outputting the skin material containing the dynamic reflectivity field. And finally, binding the optimized skin with a skeleton animation system in real time, and outputting a rendered digital human. Through layered optical modeling, dynamic sampling optimization, hardware acceleration rendering and the like, the skin optical optimization result is deeply embedded into the digital human modeling process, the skin rendering precision is improved, the dynamic adaptability is enhanced, and the problems that in the prior art, the skin of a digital human is not real, dynamic response is delayed, and the digital human is not real are solved. The skin texture and the muscle movement are not synchronous, and the like.

The invention relates to the technical field of computers, in particular to a skeletal animation generation method and device, a computer program product and electronic equipment. The skeletal animation generation method comprises the steps of obtaining a scaling parameter of a to-be-scaled skeletal, adding the scaling parameter to original skeletal data to obtain target skeletal data, and generating an initial animation based on the target skeletal data; analyzing the initial animation to obtain stretching transformation data of each skeleton; based on the stretching transformation data, carrying out stretching component separation processing on a local space matrix of a skeleton in the initial animation to obtain effective stretching data and local space matrix data after the effective stretching data is removed; and according to the effective stretching data and the local space matrix data, generating a skeleton zooming animation in the game engine. According to the invention, the manufacturing effect and efficiency of the skeleton zooming animation can be improved.

The application provides a method and device for generating skeletal animation of a digital character suitable for Unity development, comprising: obtaining motion requirement information of the digital character and encapsulating the information into skeletal animation generation instructions of a specific data structure; converting the skeletal animation generation instructions into structured skeletal animation generation prompt word data packets; generating a BVH format skeletal animation file according to the skeletal animation generation prompt word data packets; parsing the BVH format skeletal animation file to obtain a skeletal structure and animation data; performing T-Pose difference compensation between a T-Pose of the BVH format file and a standard T-Pose of a Unity Avatar, adapting the skeletal structure of the BVH format skeletal animation file to a skeletal structure of a digital character VRM model, and generating an AnimationClip object of the digital character VRM model according to the adaptation result and the animation data; and controlling the skeletal animation to play on the digital character VRM model according to the generated AnimationClip object of the digital character VRM model, and applying a rotation compensation matrix to transform the skeleton of each frame of animation during the animation playing process.

The invention discloses a data processing method, electronic equipment, a storage medium and a computer program product, and the method comprises the steps: obtaining a token sequence which is obtained through the conversion of skeleton animation data of a first digital human; dividing tokens in the token sequence into a plurality of clusters; predicting a cluster center of each cluster in the plurality of clusters through an expert network in the multi-expert network model to obtain a first prediction value of each cluster center; and for each token in the token sequence, an estimated value of each token is obtained based on the first predicted value of the clustering center corresponding to each token and the compensation value of each token, the compensation value is used for compensating the difference between each token and the clustering center, and the estimated value of each token is used for generating the action of the first digital human. According to the invention, the searching and positioning requirements of a user in an emergency can be met, and the sensing and positioning capabilities of the terminal are improved.

The application relates to the technical field of virtual reality, and provides a three-dimensional human body model and skeleton synchronous updating method and an electronic device. An initial three-dimensional human body model and a preset skeleton are initialized to determine a plurality of target geometric vertices associated with each skeleton node, an influence weight corresponding to each target geometric vertex, and a scaling ratio between a child skeleton node and a parent skeleton node. The initial three-dimensional human body model is driven in a non-skeletal animation mode, the three-dimensional coordinates of the geometric vertices after driving are obtained, the three-dimensional coordinates of each skeleton node are reversely calculated according to the three-dimensional coordinates of the geometric vertices after driving and the initialization result, the skeleton structure of the preset skeleton is updated according to the three-dimensional coordinates of each skeleton node, a skeleton matching the target three-dimensional human body model is obtained, the consistency of the skeleton in the model animation process is ensured, the synchronous updating of the skeleton after the driving of the three-dimensional human body model is realized, and the authenticity of the model when performing skeletal animation based on the updated skeleton is improved, and the storage space occupied by the animation data is saved.

The embodiment of the invention provides an animation multi-thread updating method, system and device and a storage medium, relates to the technical field of game animation and is applied to an electronic device, and the electronic device runs a main thread and a plurality of sub-threads. The method comprises the steps that when a main thread conducts scene updating, acquired to-be-updated skeletal animation data is distributed to task data lists corresponding to multiple sub-threads in a balanced mode; if the sub-thread is not in the updating state currently, waking up the sub-thread to update the to-be-updated skeletal animation data; if the sub-thread is currently in the updating state, updating the to-be-updated skeletal animation data by utilizing the sub-thread; and after the scene of the main thread is updated, synchronizing the skeleton animation data updated by the sub-thread into the main thread. In this way, updating is conducted while obtaining is conducted, the spare time of the sub-threads is shortened, the main thread is synchronized in the process of waiting for calculation of the sub-threads, the generated data are synchronized in advance by fully utilizing the spare time, the degree of parallelism is improved, and therefore the multi-thread updating efficiency is improved.

The invention discloses a rendering and animation processing system and method for a multi-source heterogeneous 3D model, electronic equipment and a storage medium. The rendering and animation processing system comprises a unified abstraction layer module, a material mapping engine module, a skeleton animation processing module and a rendering module. The unified abstraction layer module executes standardized conversion from original data to internal scene data; the material mapping engine module maps an original material into an internal material with complete PBR parameters through a material processor with a built-in rule base; the skeletal animation processing module realizes a smooth animation effect by executing skeletal matrix calculation and an animation state machine; and the rendering module transmits the 3D model data processed by the unified abstraction layer module, the material mapping engine module and the skeletal animation processing module to the GPU in real time, and executes rendering calculation of the 3D data so as to output an accurate and vivid rendering result. According to the invention, processing and rendering display of 3D data in various formats can be efficiently, accurately and visually completed.

The invention provides a controllable digital human video generation method and device, equipment and a storage medium. The method comprises the following steps: acquiring an initial two-dimensional image and initial video data; the initial two-dimensional image comprises a first target body; the initial video data comprises a limb movement video of a second target body; based on the initial two-dimensional image, determining a target 3D digital person matched with the first target body; based on a limb movement video contained in the initial video data, determining a skeleton animation sequence of limb movement of a 3D skeleton corresponding to the second target body; based on the skeletal animation sequence, performing skeletal redirection processing on the target 3D digital human to generate a target video of limb movement of the target 3D digital human in a target three-dimensional scene; wherein the limb movement of the target 3D digital human in the target video is matched with the limb movement of the 3D skeleton of the skeleton animation sequence.

The application discloses an animation generation method and device of a model, a storage medium and an electronic device. The method comprises the following steps: acquiring a plurality of first models; merging the plurality of first models into a second model; determining first weight information of vertices of the second model; determining second weight information of the vertices of at least one first model based on the first weight information; and controlling the motion of each corresponding first model based on the second weight information to obtain a skeletal animation of each first model, wherein the skeletal animations of the plurality of first models constitute a broken animation of the second model. The application solves the technical problem of low animation production efficiency of a model.

An animation playing method, an electronic device and a computer readable storage medium, the method comprising: playing a first animation, the first animation being a video animation, and the first animation comprising a first object; receiving a first interaction operation of a user for a first object, wherein the first interaction operation is an operation performed on a first part of the first object; and in response to the first interaction operation, playing a second animation, the second animation being a skeletal animation, and the second animation comprising an action corresponding to the first part. The method can improve the interactivity of the animation and improve the user experience.

The present disclosure provides a motion capture redirection method and device, relates to the technical field of artificial intelligence, in particular to the technical fields of computer vision, augmented reality, virtual reality, deep learning and the like, and can be applied to metaverse, virtual digital people and the like. It comprises: obtaining a first bone node in a first skeletal animation, obtaining a second bone node and a third bone node in a second skeletal animation, the second skeletal animation being obtained by performing rotation-consistent redirection on the first skeletal animation, the first bone node and the second bone node being bone nodes of the same part, calculating incremental rotation information of the third bone node according to first position information of the first bone node, second position information of the second bone node and third position information of the third bone node, and performing optimization processing on original rotation information of the third bone node according to the incremental rotation information to obtain a redirected third bone node, thereby avoiding loss of semantic information and improving the reliability of the redirection.

The invention belongs to the technical field of three-dimensional images, and discloses an interactive generation and arrangement method for a three-dimensional martial arts action sequence. Comprising the following steps: acquiring skeletal animation data of a martial art character, defining a plurality of virtual stiffness transmitters on a martial art character skeletal system corresponding to the skeletal animation data, binding each virtual stiffness transmitter to a preset skeletal node, constructing a stiffness propagation curve along a character skeletal link, and calculating a stiffness flow field vector field on each time sampling point; setting a physical agent model; in a sequence playing process, converting the vector field of the force flow field into direction force and torque applied to each clothes control point in a physical agent model, and performing simplified collision detection and response on main limbs of the martial art role; obtaining a motion trail of each clothes control point; and mapping to a low-resolution clothing preview model to generate a clothing dynamic deformation effect, thereby realizing interactive generation and arrangement for the three-dimensional martial arts action sequence.

The application relates to a Web front-end-based interaction method, system and electronic equipment, which calls a terminal camera through a browser, acquires a video stream of a user, and processes the video stream at a browser front end to extract human key points; through a layered action mapping engine, the human key points are mapped into skeleton animation parameters of a virtual image; according to preset attributes of a virtual article and the skeleton animation parameters, the relative poses of the virtual article and the virtual image are calculated; in a browser environment, according to the relative poses, an interaction picture of the virtual article and the virtual image is rendered and displayed. The application solves the problems of high hardware dependency, poor cross-platform compatibility, simple interaction link, and serious delay and distortion in the prior art. Without special hardware, the application reduces the use threshold of users and realizes cross-platform compatibility based on a Web technology stack.

The invention relates to the field of 3D model rendering and interaction, in particular to a method for rendering and interacting a 3D workshop model in real time based on a webpage end. The method comprises the following steps: S1, defining a unified data format by adopting JSON Schema, converting a Node structure of an OPC UA containing a timestamp and a quality stamp into an MQTT theme path, and realizing a mapping table from a Modbus register address to a three-dimensional model component ID; s2, a color coding rule is defined, and equipment state parameters are transmitted in real time through Uniform variables; and S3, establishing a bidirectional binding relationship between the Three.js object and the OPC UA node, and driving the skeletal animation of the equipment by using an Animation Mixer. According to the invention, real-time dynamic feedback of factory equipment and an assembly line can be realized, and dynamic execution of the equipment can be fed back to a webpage end in real time through WebSocket according to a system of the equipment so as to carry out real-time skeleton animation feedback rendering.

The application provides a method for building a float glass production line visual interaction system, and relates to the field of float glass production management. The method comprises the following steps: firstly, obtaining model data containing PRB material and skeletal animation information; then, creating a three-dimensional scene through a Three.js library, determining camera attributes according to received camera parameters, and obtaining scene data containing the scene and the camera; then, analyzing the model data through the Three.js library, adding lighting and mapping, creating an animation mixer instance, triggering animation chain playback according to device runtime sequences, creating a ray detector for realizing three-dimensional scene interaction, and detecting device model intersection based on mouse interaction coordinates, so as to obtain a final scene model. The scheme can be used to effectively build a Web-side lightweight deployment, and realize animation interlocking control, interaction and display of the float glass production line visual interaction system.

The invention discloses a skeletal animation interactive display method, and relates to the technical field of skeletal display, the method is applied to an interactive display terminal, and the method comprises the following steps: the interactive display terminal generates a standardized hierarchical joint tree based on a multi-view image or a draft, distributes a skin weight by adopting a conflict area dynamic isolation and weight self-optimization algorithm, and displays a skeletal animation. Constructing a joint motion parameterized linkage rule base, and forming an adjustable skeleton skin basic structure; the interactive display terminal integrates physical motion capture data, text instruction analysis data and user operation data, synchronously drives a joint tree through a multi-source data space-time collaborative fusion engine, drives the joint tree through combination of multi-source data space-time collaborative fusion and scene adaptive weight distribution, breaks through the limitation of traditional single data driving, and improves the user experience. Space-time synchronization of three types of data of physical motion capture, text instruction analysis and user operation is achieved, then the weight is dynamically adjusted according to the scene, the scene is rapidly moved to preferentially guarantee coherence, and the scene is finely adjusted to focus on accuracy.

The invention relates to the field of biomedical engineering, and provides a multi-mode cerebellum function evaluation neurological physical examination method and system, and the method comprises the steps: guiding a patient to execute an examination task, and synchronously collecting myoelectricity and skeletal animation signals; continuously collecting signals according to a fixed time interval and a fixed time window; according to the time sequence, analyzing and processing the signal corresponding to each time window in sequence; the analysis processing comprises the steps of splicing the myoelectricity and skeletal animation signals of the current time window, and inputting the model to obtain an evaluation result corresponding to the current time window, and the evaluation result depends on an evaluation result corresponding to a preorder time window. The problems that the cerebellum function evaluation result is not comprehensive and the efficiency is low are solved.

The invention relates to the technical field of computer graphics, and provides a map generation method and device, equipment, a storage medium and a program product.The map generation method comprises the steps that firstly, a texture image of a target two-dimensional object is obtained, and brightness information of all pixels in the texture image is extracted; meanwhile, acquiring skeleton animation data for driving the target two-dimensional object, and determining a vertex normal vector which is transformed in real time along with skeleton movement; thirdly, calculating theoretical illumination intensity of each pixel in a preset virtual light source direction based on the vertex normal vector; then, the depth information of each pixel is determined by using the difference between the extracted brightness information and the calculated theoretical illumination intensity; and finally, generating a normal map for illumination rendering according to the depth information. According to the method and the device, the normal chartlet adaptive to dynamic deformation of the skeletal animation can be generated, and the problems of high manufacturing cost and incapability of matching a static chartlet with a dynamic posture in related technologies are solved.