A method for generating a representation of a three-dimensional protective device includes accessing a scan of anatomical data of a target and identifying a reference model of a closest size or proportion to a size or proportion of the target. The method further includes creating a boundary of a three-dimensional protective device using the reference model and the scan of anatomical data of the target. Additionally, the method includes generating a representation of a continuous, three-dimensional surface of the three-dimensional protective device that corresponds to the scan of anatomical data and the reference model within the boundary of the three-dimensional protective device.

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.

A system is provided for generating a custom article to fit a target surface. During operation, the system compares an input dataset with a number of cut template cut meshes. A respective cut template cut mesh includes one or more cutting paths that correspond to a boundary of the mesh. Next, the system identifies a template cut mesh that produces a closest match with the input dataset, and applies global geometric transformations to the identified template cut mesh to warp the template cut mesh to conform to the input dataset. The system further refines and projects a set of boundary and landmark points from the template cut mesh to the input dataset to define cutting paths for the input dataset. Next, the system applies cutting paths to the input dataset to produce a cut-and-trimmed mesh.

Managing volumetric data, including: defining a view volume in a volume of space, wherein the volumetric data has multiple points in the volume of space and at least one point is in the view volume and at least one point is not in the view volume; defining a grid in the volume of space, the grid having multiple cells and dividing the volume of space into respective cells, wherein each point has a corresponding cell in the grid, and each cell in the grid has zero or more corresponding points; and reducing the number of points for a cell in the grid where that cell is outside the view volume.

Various implementations or examples set forth a method for scanning a three-dimensional (3D) environment. The method includes generating a 3D representation of the 3D environment that includes one or more 3D meshes. The method also includes determining at least a portion of the 3D environment that falls within a current frame captured by the image sensor. The method further includes generating one or more additional 3D meshes representing the at least a portion of the 3D environment and combining the one or more additional 3D meshes with the one or more 3D meshes into an update to the 3D representation of the 3D environment.

Described herein are techniques for segmenting a mesh to reduce or remove elongated shapes, to enable texturing a three-dimensional (3D) mesh. An embodiment described is a method in which one or more processing devices perform operations that include accessing segments of the 3D mesh and detecting that a first segment is elongated. The operations include modifying the segments of the 3D mesh by subdividing the first segment into two or more sub-segments, based on the first segment being elongated. The operations include assigning, for each 3D vertex of the two or more sub-segments, respective two-dimensional (2D) coordinates in a texture map. The operations further include applying a texture to the 3D mesh. Application of the texture involves mapping the 3D vertices of the two or more sub-segments based on the respective 2D coordinates corresponding to the 3D vertices of the two or more sub-segments according to the texture map.

A method for adjusting point cloud density, an electronic device, and a storage medium are provided. In the method an initial point cloud map and a distance determination threshold of a robot are obtained. A plurality of target regions in the initial point cloud map are determined, and an environmental complexity value of each target region is calculated. The initial point cloud map is divided into submaps, and a point cloud density coefficient of each submap is determined. The initial point cloud map is adjusted according to the point cloud density coefficient and the target point cloud map is obtained. By utilizing such method, adjustment efficiency and an accuracy of point cloud density can be improved.

A method of compensating for shrinking and distortion of an object resulting from a manufacturing process. A scan is performed of an object following a manufacturing process to produce scan data. The scan data is aligned to a part mesh of the object. The part mesh is adjusted to substantially coincide with the scan data by moving part mesh vertices. Delta vectors are computed by subtracting initial part mesh vertex positions from final part mesh vertex positions. The inverse of the delta vectors are applied to the preprocessed part mesh to give a scan adjusted pre-processed shape.

A computer-implemented method includes obtaining an input polygon mesh representing at least part of a three-dimensional scene and comprising a plurality of input polygons, and obtaining mapping data for mapping at least part of an image to a region of the input polygon when the three-dimensional scene is rendered. Said region extends at least partway across the plurality of input polygons. The method includes using the mapping data to generate one or more test polygons to match or approximate said region of the input polygon mesh. Each of the generated test polygons is distinct from each of said plurality of input polygons.

Disclosed are various approaches for automatically assigning weights to vertices of a skin or mesh that control how said vertices in the 3D model move under the influence of skeletal rotation and translation. A computing device can receive a first model weightings matrix. Next, the computing device can include adjusting the number of rows in the first model weightings matrix to generate an adjusted model weightings matrix with a number of rows that matches an input number of rows for a machine-learning model, each row in the adjusted model weightings matrix representing a vertex of a mesh applied to a three-dimensional model. Then, the computing device can apply the machine learning model to the adjusted model weightings matrix, to generate an output polygonal mesh model weightings matrix. Subsequently, the computing device can generate a second polygonal mesh model weightings matrix by adjusting the number of rows of the machine learning model output weightings matrix to match the number of rows of the initial polygonal mesh model weightings matrix.