Abstract: A method of performing multicast broadcasting of a plurality of streams corresponding to an event is disclosed. The plurality of data streams corresponding to the event are received. Each of the plurality of streams has a different type or format. A multicast timecode is determined based on a synchronization time for each of a plurality of buffers associated with the plurality of streams. A new data stream is generated. The new data stream includes the plurality of data streams and the multicast timecode.

Abstract: An interactive tile-based ML terrain generation method is disclosed. At a first phase of a painting of a digital environment using a brush tool, a modification to a terrain surface of the digital environment is approximated. The approximating includes decomposing a stroke of the brush tool into one or more stamps. Each of the one or more stamps changes a height of a portion of terrain surface as the brush tool passes over the portion of the terrain surface. At a second phase of the painting of the digital environment, details are added to the portion of the terrain surface passed over by each of the one or more stamps. The adding of the details includes dividing work associated with the adding of the details into one or more tiles and processing the one or more tiles.

Abstract: A method of rendering a scene in a three-dimensional environment using a plurality of metaframes is disclosed. Data from digital objects within a three-dimensional (3D) environment is loaded. Motion for the digital objects is determined. The determining of the motion includes applying simulation or physics logic to the data. A plurality of metaframes is generated based on a plurality of scene graphs captured at a plurality of points in time. Each of the metaframes includes data describing position, scale, or rotation of the digital objects within the 3D environment at a point in time of the plurality of points of time. The plurality of metaframes is organized into a queue of metaframes. The plurality of metaframes is distributed to one or more rendering nodes in response to dequeuing of the metaframes from the queue by the one or more rendering nodes.

Abstract: An artificial intelligence (AI) training method is disclosed. Training data associated with a training task is received. The training data is categorized into a plurality of categories. A set of category groups are generated, wherein each category group of the set of category groups includes one or more of the plurality of categories. A first AI system is trained for the training task using a first subset of the training data. The first subset of the training data corresponds to the one or more of the plurality of categories included in a first group of the set of category groups. A second AI system is trained for the training task using a second subset of the training data. The first AI system is used to generate a first output for the task and the second AI system to generate a second output for the task.

Abstract: A method of spawning a digital island in a three-dimensional environment is disclosed. Data describing a three-dimensional environment is accessed. The data is partitioned into a plurality of contexts based on properties identified in the data, the properties corresponding to surfaces or objects in the three-dimensional environment. One or more values of one or more traits corresponding to a context of the plurality of context are identified. A digital island is matched to the context. The matching includes analyzing one or more conditions associated with the digital island with respect to the one or more values of the one or more traits corresponding to the context. Based on the matching, the spawning of the digital island is performed in the three-dimensional environment for the context.

Abstract: A system and a method of volumetric data processing include receiving volumetric data corresponding to a digital asset, the digital asset including a plurality of frames; creating a file to represent the volumetric data in a flat file format, the flat file format representing the plurality of frames arranged in a plurality of buffers in the file, each of the plurality of buffers being assigned with a fixed number of frames; and providing the file to a client device for a rendering of the digital asset.

Abstract: A method of digital content generation is disclosed. A description of a smart volumetric layout is accessed. The smart volumetric layout includes an arrangement of one or more smart volumetric shapes. Smart shape data is associated to a volumetric shape of the one or more volumetric shapes. The smart shape data includes one or more properties and one or more behaviors. A presence of one or more digital objects is detected in the smart volumetric shape. One or more properties and the one or more behaviors associated with the smart volumetric shape are applied to the one or more digital objects.

Abstract: Methods, systems, and computer-readable media for rendering light probes in a virtual environment are disclosed. Noisy lighting data is accessed in a data structure associated with a light probe in a set of light probes in an environment. The noisy lighting data is provided as an input to a neural network. The neural network is trained to output an estimate of non-noisy lighting data based on the input. The noisy lighting data is replaced in the data structure with the estimated non-noisy lighting data.

Abstract: A method of smoothly transitioning between input devices with respect to a virtual reality environment is disclosed. A probable user input action is determined based on input data from a plurality of input devices. A best device is selected from the plurality of input devices based on a quality of a signal of the best device relative to qualities of signals of other devices of the plurality of input devices. Based on a determination that the selected best device is not the same as a previously selected best device from the plurality of devices, a transition between the previously selected device and the best selected device is determined and the transition is used to drive the probable user input action based on input data from the selected best device and input data from the previously selected best device.

Abstract: A method of determining an authenticity of a normal map is disclosed. An input candidate normal map is received. A reconstructed candidate normal map is generated based on a performance of a mathematical differentiation on an integration of the input candidate normal map. A reconstruction error is determined based on a comparison of the input candidate normal map to the reconstructed candidate normal map. An authenticity of the input candidate normal map is determined based on the reconstruction error being within a configurable threshold.

Abstract: The present invention relates to a prediction system for determining a set of subregions to be used for rendering a virtual world of a computer graphics application, said subregions belonging to streamable objects to be used for rendering said virtual world, said streamable objects each comprising a plurality of subregions. The prediction system comprises a plurality of predictor units arranged for receiving from a computer graphics application information on the virtual world and each arranged for obtaining a predicted set of subregions for rendering a virtual world using streamable objects, each predicted set being obtained by applying a different prediction scheme, a streaming manager arranged for receiving the predicted sets of subregions, for deriving from the predicted sets a working set of subregions to be used for rendering and for outputting, based on the working set of subregions, steering instructions concerning the set of subregions to be actually used.

Abstract: A method of digital content generation is disclosed. A description of a smart volumetric layout is accessed. The smart volumetric layout includes an arrangement of one or more smart volumetric shapes. Smart shape data is associated to a volumetric shape of the one or more volumetric shapes. The smart shape data includes one or more properties and one or more behaviors. A presence of one or more digital objects is detected in the smart volumetric shape. One or more properties and the one or more behaviors associated with the smart volumetric shape are applied to the one or more digital objects.

Abstract: Systems and methods for generating an extended reality (XR) user interface are disclosed. A two-dimensional data set is imported. The two-dimensional data set defines a two-dimensional user interface design layout. The two-dimensional data set includes a transition data set corresponding to a user interface element included in the design layout. The two-dimensional data set is converted into a three-dimensional data set. The three-dimensional data set defines a three-dimensional user interface design layout corresponding to the two-dimensional design layout. The converting includes identifying three-dimensional art for each of a plurality of phases corresponding to the transition data set. An XR representation of the three-dimensional data set is provided for editing using an editing application associated with one or more XR devices. Based on the editing, the three-dimensional data set is exported as one or more files that are compatible with an XR development environment.