253 results about "3d space" patented technology

The invention discloses an image processing method and device and a storage medium. The method comprises the steps of obtaining a to-be-simulated 3D convolution model and training data; decomposing the 3D convolution model into cascading of a 3D space convolution model and a 3D time convolution model to obtain a pseudo 3D cascading convolution model; training a pseudo 3D cascade convolution modelby using the training data, and obtaining parameters of a 3D spatial convolution model and a 3D time convolution model; converting the 3D space convolution model and the 3D time convolution model intoa 2D space convolution model and a 2D time convolution model; setting a feature rearrangement rule for the 2D spatial convolution model and the 2D time convolution model; mapping model parameters ofthe 3D spatial convolution model and the 3D time convolution model into parameters of a 2D spatial convolution model and a 2D time convolution model to obtain a 2D cascaded convolution model; and performing convolution operation on the image by using the 2D spatial convolution model and the 2D time convolution model. By means of the mode, image processing conducted through 3D convolution operationcan be achieved through the 2D convolution model.

A computer-implemented method for 3D reconstruction of a target is provided, comprising obtaining an initial global reconstruction of the target in a 3D space, inferred by a global machine learning model; providing, to a user, an initial visualisation of the target based on the reconstruction; receiving, from the user, at least one indication of at least one point of interest in the visualisation; resampling at least one first subsection of the target based on the at least one point of interest to obtain local data, wherein the local data is associated with the subsection based on spatial information that associates the local data with a point in 3D space; inputting the resampled local data and spatial information into a local feature machine learning model to obtain at least one 3D reconstruction of the target, wherein the local feature machine learning model has been trained to output a target reconstruction from local data of resampled subsections, and wherein the 3D coordinate system of the local 3D reconstruction aligns with the global 3D reconstruction; and merging the global 3D reconstruction with the local 3D reconstruction. A corresponding computer system and computer readable medium may also be provided.

Provided herein are systems for determining a location of a gross target volume of a patient. In some examples, systems can include one or more processors that are configured to obtain image data associated with a plurality of images of a lesion of a patient. For each image, the one or more processors can be configured to backproject points representing the lesion into the 3D space to determine a plurality of distribution confidence values for a subset of voxels within the three-dimensional space. The one or more processors can be configured to determine a three-dimensional confidence distribution based on confidence values from the plurality of distribution confidence values corresponding to each voxel of the 3D space and determine a position of the lesion within the 3D space based on the 3D confidence distribution.

The invention provides a computer implementation method and device for determining space occupation information, equipment and a medium, multiple groups of binocular images collected by binocular cameras arranged in different directions of a moving body can be acquired, then image features and depth features of each group of binocular images are determined based on the multiple groups of binocular images, and then the space occupation information is determined. And projecting the image features and the depth features of each group of binocular images to an overlook coordinate system, determining target aerial view features in the overlook coordinate system, and finally, determining space occupation information in the look-around space of the moving body according to the target aerial view features. The target aerial view feature reflects the 3D space information around the moving body only through the 2D format, the storage space occupied by the 3D space information in the calculation process and the calculation complexity are reduced, and the calculation precision and the calculation efficiency of determining the space occupation information based on the target aerial view are further improved.

Apparatuses, systems, and techniques of using one or more machine learning processes (e.g., neural network(s)) to predict occupancy using an image input. In at least one embodiment, image data is processed using a neural network to predict occupancy in a 3D voxel space. In at least one embodiment, image data is processed using a neural network to detect objects in a 3D space.

The application discloses an intelligent path planning method and system for a mechanical arm spray head of a deicing vehicle, and can realize automatic and accurate deicing on a complex three-dimensional surface of an airplane. The method comprises the following steps: target surface extraction and reconstruction are performed on a deicing area of the surface of the airplane to generate a continuous three-dimensional surface; the three-dimensional surface is mapped to a two-dimensional parameter plane by surface parameterization; a 2D waypoint sequence is generated on the two-dimensional parameter plane in combination with the effective spraying width of the nozzle; 3D space inverse mapping is performed based on the 2D waypoint sequence, the spray head posture of the deicing vehicle is aligned based on the result of the inverse mapping, and the three-dimensional target posture of the nozzle at each waypoint is obtained; the target posture of the nozzle is converted into specific angle instructions of each joint of the mechanical arm of the deicing vehicle; on the basis of the joint angle instructions, joint trajectory smoothing and S-type speed planning are performed, and finally the action path of the spray head of the mechanical arm of the deicing vehicle is generated.

The application provides a large scene graph switching method, system and device and a storage medium, and the method comprises the following steps: S1, constructing a point cloud map and a graph database of a large scene; S2, robot positioning according to the graph map and real-time switching of the graph. The application firstly cuts the high-precision point cloud map of the complete large scene according to the graph, which is used for constructing the graph database of the complete large scene; then dynamically loads the graph around the current position of the robot according to the graph database, which is used for composing the graph map of the local large scene, and is used for real-time calculation of the position of the current robot in the large scene; and according to the current robot position and the predicted action path, it is decided which graphs in the graph database are switched to at present, and the graph map of the local large scene is updated in real time; the robot can realize fast and real-time graph switching in the super large scene without feeling, and accurate 3D space positioning can be realized on the hardware device with limited computing power.

A computer-implemented method is provided for acquiring a set of x unique tracking constellations in a predefined 3D space, each constellation for a corresponding wearable tracking device used to track a wearer in a 3D environment. Each unique tracking constellation includes a predefined number n tracking objects. A set of y discrete available locations is defined for locating the tracking objects within the predefined 3D space. A minimum number m of tracking objects is defined, wherein the minimum number is less than or equal to the predefined number n of tracking objects. For each unique tracking constellation, a unique discrete available location from the set of y discrete available locations is assigned to each tracking object of the tracking constellation to acquire the unique tracking constellation. The assigned location for any minimum number m of tracking objects in each unique tracking constellation is unique within the set of x unique tracking constellations.

A head-wearable apparatus improves user interactions with virtual interface elements in augmented reality (AR) environments. The apparatus tracks hand movements in 3D space, calculating velocity vectors and positions of fingers. For each virtual interface element, it determines a UI-to-finger vector and calculates alignment with the finger's velocity vector. Interaction zones are dynamically adjusted based on this alignment and velocity magnitude. The system evaluates consistency between finger movement and element locations to predict intended targets. Interactions are triggered when fingers enter adjusted zones of predicted targets. This approach reduces erroneous selections and improves interaction accuracy, even for closely-spaced elements. The invention applies to various AR scenarios, enhancing user experiences in applications like gaming and education.

A method of mesh processing includes receiving coded information of a mesh, the coded information including position connectivity of a plurality of 3D vertices of a mesh in a 3D space, and a correspondence of the plurality of 3D vertices to UV vertices in a UV space for the mesh; determining UV connectivity of the UV vertices; determining, based on the coded information, a first initial UV vertex in a first UV chart in the plurality of UV charts; determining first UV vertices in the first UV chart according to a traversing order of 3D vertices corresponding to the first UV vertices in the first UV chart, the traversing order starting from the first initial UV vertex and traversing each UV vertex in the first UV chart; decoding, from the coded information, prediction residuals of the first UV vertices; and determining first UV coordinates of the first UV vertices accordingly.

The application relates to the technical field of computer vision, and discloses an AI analysis method for construction engineering lifeline inspection, which comprises the following steps: performing space-time registration on multi-period visual and thermal imaging data based on semantic key points, and constructing a 3D space-time difference tensor containing a bimodal evolution channel; extracting space-time features by using a disease precursor analysis model, and calculating the cross-correlation of thermal and visual features through a multi-modal fusion gate unit, so that the feature weight is dynamically modulated to suppress the thermal deformation response; and the application solves the common problem that benign respiratory interference and weak disease evolution are difficult to distinguish in a complex dynamic scene by establishing physical causal constraints and forcibly decoupling environmental thermal noise and structural intrinsic damage in the feature dimension.

A computer implemented method for rendering digital three-dimensional dental models includes receiving a first digital 3D dental model including a first dental information of a patient; receiving a second digital 3D dental model including a second dental information of the patient; generating, in the digital 3D space, a superimposed model by superimposing one of the first digital 3D dental model or the second digital 3D dental model on another of the second digital 3D dental model or the first digital 3D dental model; and arranging a 2D controller and the superimposed model relative to each other such that a position of the 2D controller defines a boundary that demarcates the superimposed model between a first zone and a second zone.

This invention discloses a pose estimation method for industrial parts that integrates neural implicit representation and MGC-SR anti-reflection constraints. The method first acquires RGB-D images and a 3D CAD model of the part to be assembled; it then extracts multimodal features using a pose prediction model based on neural implicit representation and generates an initial 6 DoF pose of the part in the camera coordinate system; it converts the depth image into an observation point cloud using camera intrinsic parameters and performs coarse alignment with the CAD model point cloud in 3D space; it constructs an anti-reflection weighted model (MGC-SR) based on multi-source geometric confidence, and introduces an adaptive weight allocation strategy based on normal consistency and depth confidence to address noise interference in industrial high-reflectivity scenarios. Using Lie group and Lie algebra theory, it iterative fine-tuning minimizes the point cloud registration error in the tangent space, outputting the final high-precision pose. This invention combines the zero-shot generalization of deep learning with the physical accuracy of 3D geometric registration, effectively solving the problems of pose jitter and insufficient accuracy of industrial metal parts in high-reflectivity, low-texture environments, and has high engineering application value.

The invention discloses a UI animation control system based on a random tilt and color change algorithm, and the system comprises an animation execution module which drives a target UI element to rotate and change color attributes through an animation complement library; the random tilt calculation module generates a random rotation axis through vector cross multiplication and instructs the animation execution module to drive the target UI element to rotate along the random rotation axis in the 3D space; the dynamic trigger module comprises a control parameter n which is calculated in real time, and is used for monitoring at least one state parameter of the target UI element, comparing the state parameter with the control parameter n, and sending a trigger instruction to the animation execution module and the random tilt calculation module when a preset condition is met, the rotation and the color attribute change of the target UI element are driven. The problems that an existing UI animation is simple in dynamic effect, single in interaction mode and incapable of meeting the dynamic and interactive requirements of a user can be solved.

This application provides a method, apparatus, device, medium, and program product for determining a vehicle cleaning path. The method maps the 3D point cloud data of the vehicle to be cleaned to a 2D space according to the Z-axis and X-axis projection directions to obtain an unobstructed area; it then segments the unobstructed area to obtain a list of cells and a scan line corresponding to each cell; using a path connection algorithm, it generates candidate cleaning paths in the 2D space based on the cell list and the scan line corresponding to each cell; finally, it maps the candidate cleaning paths to a 3D space using bivariate spline interpolation to obtain the target cleaning path. This application avoids the redundant path problem of traditional segmentation methods by mapping the vehicle's 3D point cloud data to a 2D space and then performing region decomposition and path planning; finally, it maps the paths from the 2D space back to the 3D space using bivariate spline interpolation, ensuring the continuity and coverage integrity of the cleaning path.

Systems and methods for enhanced end-to-end three-dimensional (3-D) object detection are disclosed that improve detecting objects in the 3D space from images, such as monocular camera image that may be captured during the operation the autonomous vehicles. For example, a vehicle can include a processor device detecting one or more objects in a 3D space by predicting 3D bounding boxes and predicting dense depth associated with target assignments. The target assignments correspond to the location of objects within an image of the 3D space of a surrounding environment for the vehicle. The vehicle can also include a controller device that receives the detection of the objects in the 3D space from the processor device and performs autonomous operations. The end-to-end 3D object detection techniques achieve a high level of object detection accuracy, with significant improvements compared to previous methods, due to the simplicity and optimization of its end-to-end functionality.

A method may be disclosed that includes the steps of: acquiring a camera setting value for adapting a 3D space to a screen of an electronic device, where the 3D space includes an image indicator for controlling the device; determining a density independent pixel (DP) value of the image indicator, where the DP value corresponds to a size at which the image indicator is to be displayed on the screen; acquiring a magnification for magnifying or reducing the 3D space based on the DP value of the image indicator, a size ratio of the image indicator in the 3D space, and a DP value of the electronic device; adjusting a camera setting value based on a magnification for magnifying or reducing the 3D space; and displaying, on a screen of the electronic device, an image of the 3D space that is enlarged or reduced by applying the adjusted camera setting value.

This invention discloses a PCB characteristic impedance simulation optimization method and system based on 3D modeling, relating to the field of high-speed intelligent circuit technology. The method involves acquiring measured material parameters and process deviations of the PCB to generate twin parameter vectors; constructing a local 3D subdomain model; concatenating the local 3D subdomain model with the manufacturing twin dataset to obtain multi-dimensional physical feature vectors, which are then processed to obtain a sequence of key influencing factors; processing the key influencing factor sequence using an impedance prediction proxy model to obtain the time-domain reflection impedance curve and the corresponding coordinates of 3D spatial impedance abrupt change points; adjusting the coordinates of the 3D spatial impedance abrupt change points based on an impedance reshaping strategy to obtain optimal 3D compensation parameters; reconstructing the 3D simulation model using the optimal 3D compensation parameters to obtain updated PCB manufacturing data; and outputting impedance control parameters through a target verification rule engine to accurately locate the coordinates of impedance abrupt change points in 3D space, thereby improving design efficiency and quality.

An electronic device may include a display capable of providing a stereoscopic image to a user. The electronic device may comprise a processor. The processor may be configured to display an object on the display. The processor may be configured to receive a first input for moving the object. The processor may be configured to display, on the display, as a stereoscopic image, an executable object for an executable function related to the object, in response to the object moving along a perpendicular direction perpendicular to one surface of the display by means of the first input. The processor may be configured to execute the function in response to a second input for linking the object to the executable object.

This invention provides an atomic-level electron tomography 3D reconstruction method. Its core is to match the simulated projection of an atomic model with experimental images through iterative optimization. The method first constructs a 3D space based on the sample contour and initializes the atomic model parameters. Then, it acquires experimental images from multiple angles and their imaging parameters. In each iteration, a simulated projection image is generated based on the current atomic model and imaging parameters, and the difference between it and the corresponding experimental image is calculated as the loss value. An optimization algorithm dynamically adjusts atomic parameters (position, size, etc.) and imaging parameters (such as focus distance and aberrations) to minimize the total loss. This process includes intelligent simplification steps, which can merge or delete atoms to optimize model complexity. Finally, using the converged high-precision atomic model, 3D reconstructed images with arbitrary viewpoints and depths can be generated. This method can achieve high-precision atomic-level 3D reconstruction without completely relying on 360-degree scan data, helping to reduce data acquisition costs.

The invention discloses a method and equipment for verifying radar point cloud data. The method comprises a multi-modal data acquisition step: acquiring multi-modal data at least comprising data of a real road scene acquired by a plurality of different types of sensors arranged on an autonomous vehicle; a scene truth value data generation step of generating scene truth value data of a road by using a voxel occupancy generation neural network based on velocity representation based on the acquired multi-modal data; and a point cloud data verification step: comparing the radar point cloud data generated by the radar of the autonomous vehicle with the scene truth value data to obtain a comparison result of the difference between the radar point cloud data and the scene truth value data so as to generate a verification result representing the accuracy of the radar point cloud data. According to the method and the device provided by the invention, various sensor data are fused, the road scene truth value data are generated by utilizing the voxel occupancy generation neural network, and the accuracy of the radar point cloud data is verified in the 3D space by utilizing the road scene truth value data, so that the radar point cloud data are accurately matched with a real road scene.

Aspects concern a virtual reality control device comprising one or more sensors configured to sense sensor data allowing determining the 3D position of the virtual reality control device in 3D space, at least one rotary wheel switch; and an output interface configured to output the sensor data from the one or more sensors and information about a rotation of the at least one rotary wheel switch.

The systems and methods display, by at least one processor on a first portion of a real-world environment visible on a display of a user device, one or more virtual objects at a first virtual coordinate in three-dimensional (3D) space. The systems and methods receive a request to move the one or more virtual objects to a second virtual coordinate in 3D space. The systems and methods in response to receiving the request, maintain display of the one or more virtual objects at the second virtual coordinate as a second portion of the real-world environment is visible on the display of the user device.

A method for training a 3D space consistent medical volume data generative model is provided, which is performed by one or more processors and which includes generating a synthetic volume data using a generator network, receiving real volume data, generating a plurality of 2D images based on the synthetic volume data and the real volume data, discriminating whether each of the plurality of generated 2D images is real or fake by using a plurality of discriminator networks, and updating the generator network based on discrimination results of the plurality of discriminator networks.

The invention provides a uniform video segmentation method and system based on sparse space-time propagation. The method comprises the following steps: generating an initial segmentation mask for a video frame; extracting spatio-temporal context features of a current frame and a historical frame by using a 3D spatio-temporal convolution module, enhancing the spatio-temporal context features, and fusing and coding the spatio-temporal context features and an initial segmentation mask of the current frame into a memory containing spatio-temporal contexts; aggregating the global multi-frame spatio-temporal information into each memory frame during memory construction; the space-time aggregation reading module executes space-time aggregation reading based on a double-attention mechanism, and retrieves most relevant information from a memory bank; and performing sparse matching and fusion by adopting a non-local mechanism, and outputting a final video segmentation result. According to the method, multi-frame spatio-temporal information is efficiently coded into a memory bank, accurate and efficient sparse connection is established between the query frame and the memory bank by using a dynamic 3D spatio-temporal convolution module and a spatio-temporal aggregation reading strategy, video-level spatio-temporal relation modeling is realized, and a relatively high processing speed is kept while the segmentation precision is remarkably improved.

The invention discloses a panoramic sound audio generation method and system based on artificial intelligence, and a storage medium, and the method comprises the following steps: S1, inputting an original audio signal and scene parameters, obtaining the time domain-frequency domain features and space scene features of the original audio signal through a multi-modal feature extraction algorithm, carrying out weighted fusion on the time domain-frequency domain features and the space scene features to obtain fusion features; s2, constructing a mathematical expression basis of a 3D space sound field model based on a spherical harmonic function, and mapping fusion features to three-dimensional space coordinates and the 3D space sound field model through a sound field modeling algorithm; and S3, converting the 3D space sound field model into multi-channel panoramic sound audio output according to the parameters of the target playing equipment by using an adaptive rendering algorithm. According to the method, feature extraction, fusion and sound field modeling are carried out by inputting the original audio signals and scene parameters, automatic panoramic sound audio generation is realized based on adaptive rendering conversion output, and the method has the advantages of automation, high efficiency, high precision and the like.

The present application belongs to the technical field of image processing, and specifically relates to a three-dimensional face model automatic generation method, which is characterized by the following specific steps: data loading processing, user model generation based on computer vision, user model grid re-topology, model grid local shape optimization, model grid fusion splicing, and output result model. The grid generation method ensures 2D mapping accuracy according to face key points; the grid deformation and smoothing method makes the user model and the standard face model closer in 3D space under the premise of reasonable deformation, so that the mapping is more accurate; the re-topology model grid local shape optimization utilizes original grid information to correct the grid deformity and improve the quality of the model. The model grid fusion splicing adopts the grid deformation and grid smoothing method, so that the output result meets the design requirements, guarantees the integrity and high quality of the model, and reduces the post-processing work.

The present invention relates to systems and methods for determining a location of a gross target volume of a patient. In some examples, a system can include one or more processors configured to obtain image data associated with a plurality of images of a lesion of a patient. For each image, the one or more processors can be configured to backproject points representative of the lesion into a 3D space to determine a plurality of distribution confidence values for a subset of voxels within the three-dimensional space. The one or more processors can be configured to determine a three-dimensional confidence distribution based on the confidence values from the plurality of distribution confidence values corresponding to each voxel of the 3D space and determine a location of the lesion in the 3D space based on the three-dimensional confidence distribution.

The application discloses a face anti-counterfeiting method and device and a storage medium. The face anti-counterfeiting method comprises the following steps: acquiring a to-be-detected image collected by a 2D monocular camera; acquiring a depth factor corresponding to each pixel coordinate point of the to-be-detected image through a preset face depth model; converting the to-be-detected image into a 3D space information image according to the depth factor and preset camera parameters; judging whether the converted 3D space information image is a plane false face; and if the 3D space information image is not a plane false face, judging whether the to-be-detected image is a three-dimensional false face through a preset three-dimensional anti-counterfeiting model. Thus, the face depth model and the three-dimensional anti-counterfeiting model are used to realize two-dimensional and three-dimensional anti-counterfeiting of the image through the 2D monocular camera. The hardware requirement for the camera is reduced without the action cooperation of the verifier, the face verification efficiency is improved, and the face anti-counterfeiting accuracy is improved.

Disclosed herein is a three-dimensional (3D) display apparatus and method based on a low-coherence light source. The 3D display apparatus based on a low-coherence light source may include a first modulation panel for generating and displaying two-dimensional (2D) amplitude information using a self-emissive low-coherence light source and a second modulation panel for converting the 2D amplitude information of the first modulation panel into voxels in a 3D space by modulating the 2D amplitude information into phase information.