In one embodiment, a method for generating a three-dimensional (3D) anatomical map, including applying a trained artificial neural network to (a) a set of two-dimensional (2D) fluoroscopic images of a body part of a living subject, and (b) respective first 3D coordinates of the set of 2D fluoroscopic images, yielding second 3D coordinates of the 3D anatomical map, and rendering to a display the 3D anatomical map responsively to the second 3D coordinates.

A method for detecting an operating terrain is provided. The method includes obtaining point cloud data of an operating region that are collected by a laser radar at a current time, including three-dimensional coordinates of a plurality of sampling points. The operating region is divided into a plurality of grids, each having a corresponding height value. The method includes for any grid determining an input point of the grid from the plurality of sampling points, based on the three-dimensional coordinates. The method includes determining a type of the input point, based on a height coordinate of the input point and the height value of the grid. The type includes a noise point and a ground point. The method includes in response to determining that the input point is the ground point, updating the height value of the grid based on the height coordinate of the input point.

An electronic apparatus performs a method of representing a 3D shape that includes: dividing a 3D space enclosing the 3D shape into a plurality of 3D spaces with a hierarchical octree structure; generating local implicit functions, and each of the local implicit functions corresponds to a respective 3D space of the plurality of 3D spaces; and reconstructing a representation of the 3D shape from the local implicit functions with the hierarchical octree structure. In some embodiments, the 3D space is recursively subdivided into the child octants according to the surface occupancy and richness of the geometry of the 3D shape, and a respective local implicit function is generated corresponding to a geometry of a part of the surface.

Methods and systems are provided, which convert points in a cloud into a model for 3D printing in a computationally efficient manner and while maintaining and possibly adjusting shape, volume and color information. Methods include deriving, from the points, a crude watertight mesh with respect to the points, e.g., an alpha shape, determining, using normal vectors associated with the points, locations of the points with respect to the mesh (e.g., as being inside, outside or within the model) and using the derived mesh to define the model with respect to the determined locations of the points. Combining the computational geometry approach with the field approach is synergetic and results in better information content of the resulting model for 3D printing while consuming less computational resources.

The point cloud scan image data first is structured with a x-y-z coordinate system, then split into smaller Cluster Bounds (CB) volumes and a CB x-y-z is imposed on the CB centroid. The Euclidean x-y-z distance (ED) is calculated for each data point. Only points within Radial Distance (RD cylinder) are retained/processed. Data points within RD are weighted; points closer to centroid having higher weights. Each data point has Weighted Value WV (square of the inverse of the x-y-z distance). Each x, y, z has Weighted Average (WAV) per axes. WAV is sum of each original point coordinate times WV, divided by sum all WVs. Resultant is one subsampled point per axis. One WAV per CB is selected based upon axis nearly orthogonal to x, y, z WAV points. All CBs subsampled in parallel. Subsampled output comma separated coordinate file for CAD program.

Disclosed is a method for generating high resolution point cloud data for electro-anatomical mapping comprising receiving sparsely measured point cloud data having a plurality of data points. Surface mesh data comprising mesh points defining triangles on a myocardial surface is generated. The point cloud data is mapped to the surface mesh data. For each point of the surface mesh data that cannot be mapped to the point cloud data because there is a missing data point in point cloud data, an interpolation operation is performed based on the point cloud data within the neighbourhood of the point to generate a value for the missing data point. The interpolation operation is repeated N times. For every repetition, a difference between the value for the missing data point generated from the current iteration and the value for the missing data point generated from the immediately preceding iteration is compared, until the difference is below a threshold.

A device for defining a generic movement sequence on a generic model includes a means for acquiring the position of a reference element moving over a surface. The reference element is configured to perform an actual movement sequence. The device also includes a means for recording the sequence of actual movements, a means for acquiring a three-dimensional representation of the surface, a means for adapting the generic model to the three-dimensional representation of the surface, and a means for defining a generic movement sequence on the generic model by applying, to the real movement sequence, the adaptation between the generic model and the three-dimensional representation of the surface.

A method for processing point cloud data according to embodiments may encode and transmit point cloud data. The method for processing point cloud data according to embodiments may receive and decode point cloud data.

An embodiment of this application discloses a three-dimensional reconstruction method. The method in this embodiment of this application includes: obtaining an image of a first object and a camera pose of the image; determining a first normalized object location field NOLF image of the first object in the image by using a first deep learning network, where the first NOLF image indicates a normalized three-dimensional point cloud of the first object at a photographing angle of view of the image; determining, from a plurality of three-dimensional models in a model database based on the first NOLF image, a first model corresponding to the first object; determining a pose of the first object based on the first model and the camera pose of the image; and performing three-dimensional reconstruction on the first object in the image based on the first model and the pose of the first object.

A hair rendering method includes acquiring a target video containing hair information, and selecting a target image frame from image frames of the target video, acquiring a texture image of the target image frame, wherein the texture image is an image in a texture format which records motion states and state change information of one or more pixel points in the target image frame.

The method further includes acquiring a first target motion state and target state change information of a first target particle region from the texture image; determining a second target motion state of the first target particle region in a next image frame according to the first target motion state and the target state change information, and rendering the hair region by updating a motion state in the texture image according to the second target motion state.