A non-transitory computer readable medium embodies instructions that cause one or more processors to perform a method. The method includes: (A) receiving, in one or more memories, a 3D model corresponding to an object, and (B) setting a depth sensor characteristic data set for a depth sensor for use in detecting a pose of the object in a real scene. The method also includes (C) generating blurred 2.5D representation data of the 3D model for at least one view around the 3D model based on the 3D model and the depth sensor characteristic data set, to generate, on the basis of the 2.5D representation data, training data for training an object detection algorithm, and (D) storing the training data in one or more memories.

Mesh-based raw video data (or 3D video data) includes a sequence of frames, each of which includes geometry data (e.g., triangle meshes or other meshes) and texture map(s) defining one or more objects. The raw 3D video data is segmented based on consistent mesh topology across frames. For each segment, a consistent mesh sequence (CMS) is defined and a consistent texture atlas (CTA) is generated. The CMS and CTA for each segment are compressed and stored as compressed data files. The compressed data files can be decompressed and used to render displayable images.

A method of calibrating a LiDAR sensor mounted on a vehicle includes positioning the vehicle at a distance from a target including a planar mirror and features surrounding the mirror. The vehicle is positioned and oriented relative to the mirror so that an optical axis of the LiDAR sensor is nominally parallel to the optical axis of the mirror, and the target is nominally centered at a field of view of the LiDAR sensor. The method further includes acquiring, using the LiDAR sensor, a three-dimensional image of the target including images of the features of the target and a mirror image of the vehicle formed by the mirror. The method further includes determining a deviation from an expected alignment of the LiDAR sensor with respect to the vehicle by analyzing the images of the features and the mirror image of the vehicle in the three-dimensional image of the target.

Mesh-based raw video data (or 3D video data) includes a sequence of frames, each of which includes geometry data (e.g., triangle meshes or other meshes) and texture map(s) defining one or more objects. The raw 3D video data is segmented based on consistent mesh topology across frames. For each segment, a consistent mesh sequence (CMS) is defined and a consistent texture atlas (CTA) is generated. The CMS and CTA for each segment are compressed and stored as compressed data files. The compressed data files can be decompressed and used to render displayable images.

Augmenting a video stream of an environment is provided, the environment containing a private entity to be augmented. Video of the environment is processed in accordance with an entity recognition process to identify the presence of at least part of an entity in the environment. It is determined whether the identified entity is to be augmented based on information relating to the identified entity and the private entity. Based on determining that the identified entity is to be augmented, the video stream is modified to replace at least a portion of the identified entity with a graphical element adapted to obscure the portion of the identified entity in the video stream. By modifying the video stream to obscure an entity, private or personal information in the environment may be prevented from being displayed to a viewer of the video stream.

To apply an edge effect to a 3D virtual object, a display system receives user input indicative of a desired display region of a 3D virtual object, defines a bounding volume corresponding to the desired display region, and clips the edges of the 3D virtual object to the surfaces of the bounding volume. The display system applies a visual edge effect to one or more of the clipped edges of the 3D virtual object, and displays to the user of the 3D virtual object with the visual edge effect. The technique can include selectively discarding pixels along a surface of the bounding volume, based on a depth map indicative of height values of the 3D virtual object at different horizontal pixel coordinates where the visual edge effect is applied only for edge pixels not discarded.

A method includes a computing device of a computing infrastructure interpreting a request from a learning object owner computing device to make available for licensing a set of learning objects to produce an object basics record of a smart contract for the set of learning objects. The method further includes verifying, with an accreditation authority computing device of the computing infrastructure, validity of the object basics record. When the object basics record is valid, the method further includes establishing available license terms of the smart contract for the set of learning objects, establishing available payment terms of the smart contract for the set of learning objects, and causing generation of a non-fungible token associated with the smart contract in an object distributed ledger.

A method includes a computing device of a computing infrastructure interpreting a request from a user computing device of the computing infrastructure to cause a license of a set of learning objects pertaining to a common topic for use by the user computing device to produce licensee information for the set of learning objects. The method further includes identifying a non-fungible token (NFT) associated with the set of learning objects and establishing, with the user computing device, agreed licensing terms utilizing the licensee information and based on available licensing terms of a smart contract for the set of learning objects. The method further includes generating a license smart contract for the set of learning objects to include the licensee information and the agreed licensing terms and causing generation of a license block affiliated with the NFT via a blockchain of the object distributed ledger.

Augmenting a video stream of an environment is provided, the environment containing a private entity to be augmented. Video of the environment is processed in accordance with an entity recognition process to identify the presence of at least part of an entity in the environment. It is determined whether the identified entity is to be augmented based on information relating to the identified entity and the private entity. Based on determining that the identified entity is to be augmented, the video stream is modified to replace at least a portion of the identified entity with a graphical element adapted to obscure the portion of the identified entity in the video stream. By modifying the video stream to obscure an entity, private or personal information in the environment may be prevented from being displayed to a viewer of the video stream.

Methods and apparatus for providing interactive and customized experiences to clients of a media universe (MU) system. The MU system may leverage network-based computation resources and services, for example a streaming service, and a digital asset repository or repository service to dynamically provide customized and customizable experiences to clients. Clients may create or modify digital assets (e.g., 3D models of characters, objects, etc.), which may be stored to the asset repository. The MU system may dynamically render digital media content of the media universe (e.g., movies, games, etc.) that includes the clients' custom digital assets (characters, objects, backgrounds, etc.) inserted into appropriate locations, and stream the dynamically customized content to respective client devices. Effectively, a client layer of content is overlaid on a base or canonical layer of content within digital media of the media universe.