A mobile device is fitted with a camera and an extended reality (XR) software application program executing on a processor within an XR system. Via the XR software application program, techniques are performed for manipulating virtual objects in an XR environment. In one technique, the XR software application program facilitates the movement of a virtual object from a first location to a second location, within a plane parallel to a touchscreen of a mobile device, responsive to a displacement determined based on user input detected via the touchscreen.

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.

The present disclosure provides a method for correcting and encrypting space coordinates of a three-dimensional model. The method for correcting space coordinates of a three-dimensional model includes: step S1, reading information of an original coordinate frame of a three-dimensional model in a first format and the origin of coordinates of the model; reading information of nodes from three-dimensional model data in the first format, and calculating original coordinates of the nodes; step S2, calculating parameters of correction between the original coordinate frame and a target coordinate frame based on space coordinates of four or more control points in the original coordinate frame in the first format and corresponding space coordinates of the control points in the target coordinate frame in a second format, and constructing a space coordinate correction matrix; step S3, transforming and correcting the coordinates of the origin and nodes of the three-dimensional model in the first format one by one by using the space coordinate correction matrix to obtain information of coordinate points of the three-dimensional model in the second format; and step S4, storing a file of the three-dimensional model in the second format with corrected space coordinates. Thus, the production efficiency is improved.

Examples of methods for registering objects are described herein. In some examples, a method includes determining a set of overlap scores based on a set of orientations between a first bounding box of a three-dimensional (3D) object model and a second bounding box of a 3D scan of an object. In some examples, the method includes registering the 3D scan with the 3D object model based on the set of overlap scores.

A presentation device for displaying a graphical presentation of an augmented reality is disclosed. The presentation device includes a recording unit, a first display unit, and a processing unit. The recording unit is configured to capture a relative positioning of the first display unit in respect of a presentation area and capture a second set of graphical information. The processing unit is configured to generate an augmented reality based on a received dataset, supply a graphical presentation of the augmented reality by virtual mapping to the presentation area, and adjust the augmented reality and/or the graphical presentation thereof as a function of the second set of graphical information. The first display unit is at least partially transparent and is configured to display the graphical presentation of the augmented reality.

Systems and methods described herein relate to reconstructing a scene in three dimensions from a two-dimensional image. One embodiment processes an image using a detection transformer to detect an object in the scene and to generate a NOCS map of the object and a background depth map; uses MLPs to relate the object to a differentiable database of object priors (PriorDB); recovers, from the NOCS map, a partial 3D object shape; estimates an initial object pose; fits a PriorDB object prior to align in geometry and appearance with the partial 3D shape to produce a complete shape and refines the initial pose estimate; generates an editable and re-renderable 3D scene reconstruction based, at least in part, on the complete shape, the refined pose estimate, and the depth map; and controls the operation of a robot based, at least in part, on the editable and re-renderable 3D scene reconstruction.

A method of compensating for sintering warpage due to powder spreading density variations in binder jetting additive manufacturing, including receiving an initial design file defining an object geometry, representing the object geometry as a part mesh and filling the mesh with a grid of voxels to create a voxel grid, each voxel having at least one shrinkage coefficient. For each voxel, determining a distortion factor caused by a powder density variation induced during a powder spreading process and adjusting the at shrinkage coefficient of each voxel according to its respective distortion factor. Next, a shrinkage of the grid of voxels is simulated according to a sintering process. A negative compensation is applied to the voxel grid, according to the simulated shrinkage of the grid of voxels, to form a compensated voxel grid. Lastly, the change in the voxel grid is mapped to the compensated voxel grid onto the part mesh to create a pre-processed compensated part mesh.

The present disclosure provides an image processing method and apparatus, an electronic device, and a computer-readable storage medium. The method includes: obtaining a to-be-processed video comprising m frames of images, m being a positive integer greater than or equal to 2; placing a three-dimensional model on a target plane of a first frame of image of the to-be-processed video, a plurality of feature points of a model surface of the three-dimensional model falling on the target plane; determining three-dimensional coordinates of the plurality of feature points of the model surface in a world coordinate system and pixel coordinates of the plurality of feature points of the model surface on the first frame of image; determining, according to the three-dimensional coordinates of the plurality of feature points of the model surface in the world coordinate system and the pixel coordinates of the plurality of feature points of the model surface on the first frame of image, a pose of a camera coordinate system of the first frame of image relative to the world coordinate system; determining, according to the target plane, the three-dimensional coordinates of the plurality of feature points of the model surface in the world coordinate system, and the pixel coordinates of the plurality of feature points of the model surface on the first frame of image, poses of camera coordinate systems of a second frame of image to an m.sup.th frame of image of the to-be-processed video relative to the world coordinate system; and replacing the three-dimensional model with a target model and placing the target model on the world coordinate system to generate, according to the pose of the camera coordinate system of each frame of image of the to-be-processed video relative to the world coordinate system, a target video comprising the target model.

According to an embodiment, a method for providing a smart parking space guide service to provide a real-time moving route and occupancy state is executed by a parking space guide service provider server and comprises starting to trace a vehicle's moving route upon receiving the vehicle's entry event from an entry recognition device for recognizing entry of the vehicle into a parking lot, updating, in real-time, the vehicle's moving route upon real-time entry of the vehicle's moving route from at least one movement recognition device, displaying occupancy by the vehicle's parking on a pre-stored parking spot map upon sensing the vehicle's parking state from any one of at least one vehicle recognition sensor installed in at least one parking spot, and updating, in real-time, and displaying the vehicle's moving route and occupancy state on the pre-stored parking spot map.

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.