A system including server(s) configured to: receive, from host device, visible-light images of real-world environment captured by visible-light camera(s); process visible-light images to generate three-dimensional (3D) environment model; receive, from client device, information indicative of pose of client device; utilise 3D environment model to generate reconstructed image(s) and reconstructed depth map(s); determine position of each pixel of reconstructed image(s); receive, from host device, current visible-light image(s); receive, from host device, information indicative of current pose of host device, or determine said current pose; determine, for pixel of reconstructed image(s), whether or not corresponding pixel exists in current visible-light image(s); replace initial pixel values of pixel in reconstructed image(s) with pixel values of corresponding pixel in current visible-light image(s), when corresponding pixel exists in current visible-light image(s); and send reconstructed image(s) to client device.

A computer-implemented method including determining a group to which a first object belongs and a group to which a second object belongs, executing a simulation including the first object and the second object, executing a collision determination between the first object and the second object during execution of the simulation, and changing the group to which the first object belongs when a predetermined condition is satisfied. The collision determination is executed only when the group to which the first object belongs is different from the group to which the second object belongs.

Methods and systems described herein are directed to creating an artificial reality environment having elements automatically created from source images. In response to a creation system receiving the source images, the system can employ a multi-layered comparative analysis to obtain virtual object representations of objects depicted in the source images. A first set of the virtual objects can be selected from a library by matching identifiers for the depicted objects with tags on virtual objects in the library. A second set of virtual objects can be objects for which no candidate first virtual objects was adequately matched in the library, prompting the creation of a virtual object by generating depth data and skinning a resulting 3D mesh based on the source images. Having determined the virtual objects, the system can compile them into the artificial reality environment according to relative locations determined from the source images.

A system for positioning objects within an environment includes: an input unit operable to receive data representative of at least a portion of an environment comprising one or more features associated with the environment; an object determining unit operable to identify, for one or more objects, one or more features associated with each respective object, and operable to determine which of the one or more objects are to be positioned within the environment; and an object positioning unit operable to position the one or more determined objects within the environment in dependence upon at least one of the features associated with the environment and at least one of the features associated with each respective determined object, where the object positioning unit is operable to utilise a machine learning model, trained using one or more examples of one or more other objects positioned within at least a portion of one or more other environments in dependence upon at least one feature associated with each respective other environment and at least one feature associated with each respective other object as an input, to position the one or more determined objects within the environment.

In one embodiment, a method includes generating a front panel of a garment based on one or more images including the garment, generating a back panel of the garment, aligning the front panel and the back panel in a three-dimensional space so that the front panel is in front of a three-dimensional body and the back panel is behind the three-dimensional body, identifying one or more pairs of boundary segments of the front panel and the back panel, wherein each pair of boundary segments of the front panel and the back panel are to be attached together, and generating a digital garment by attaching each of the identified one or more pairs of boundary segments of the front panel and the back panel through a plurality of iterative simulations using a physics simulation model.

Disclosed are systems and method for determining information related to building materials based on determined measurements from a multi-dimensional building model comprising features and elements embodying such materials and measurements. The multi-dimensional model may be based on a plurality of received images, such as ground-based images of a building. The multi-dimensional model may be scaled, or a scale extracted based on data of the model. The multi-dimensional model may comprise architectural elements, and the scale used to determine measurements of such architectural elements. With the scaled measurements of the architectural elements in the model, product information related to multi-dimensional model and its elements may be derived and combined in alternative means.

Examples of the disclosure describe systems and methods for decomposing and sharing 3D models. In an example method, a first version of a virtual three-dimensional model is displayed via a display of a wearable head device. A request is made to a host device for data associated with a second version of the virtual three-dimensional model, wherein the second version of the virtual three-dimensional model comprises a constituent part. It is determined whether the first version of the virtual three-dimensional model comprises the constituent part. In accordance with a determination that the first version of the virtual three-dimensional model does not comprise the constituent part, a request is made to the host device for data associated with the constituent part. The second version of the virtual three-dimensional model is displayed, via the display of the wearable head device. In accordance with a determination that the first version of the virtual three-dimensional model comprises the constituent part, a request is not made to the host device for data associated with the constituent part.

A method for creating a watertight boundary between two graphical elements including the steps of displaying a first surface having a first shape and a second surface having a second shape on the display, an open space existing between the first surface and the second surface, defining a first region of the first surface, and defining a second region of the second surface, and modifying the first surface to a modified first surface such that the first region matches with the second region and the modified first surface and the second surface form a watertight connection at a modified first region and the second region, the step of modifying including geometrically matching the first region of the first surface with the second region of the second surface to establish the modified first region.

Methods and systems for generating stereoscopic content with granular control over binocular disparity based on multi-perspective imaging from representations of light fields are provided. The stereoscopic content is computed as piecewise continuous cuts through a representation of a light field, minimizing an energy reflecting prescribed parameters such as depth budget, maximum binocular disparity gradient, desired stereoscopic baseline. The methods and systems may be used for efficient and flexible stereoscopic post-processing, such as reducing excessive binocular disparity while preserving perceived depth or retargeting of already captured scenes to various view settings. Moreover, such methods and systems are highly useful for content creation in the context of multi-view autostereoscopic displays and provide a novel conceptual approach to stereoscopic image processing and post-production.

A method may receive a first three-dimensional model of at least a body part of a person. A method may receive a second three-dimensional model of a wearable device comprising a head-mounted display configured to project a display. A method may predict, by at least one machine-learning model using the first three-dimensional model and the second three-dimensional model as inputs, a plurality of contact points between the first three-dimensional model and the second three-dimensional model. A method may compute a display fit value based on the plurality of contact points.