Abstract: Methods, devices and stream are disclosed to encode and decode a volumetric content. At the encoding, the space of the volumetric content is divided in distinct sectors according to at least two different sectorizations. One atlas is generated for each sectorization or a single atlas is generated encoding all the sectorizations. At the decoding, a sectorization is selected according to the current direction and field of view, according to user's gaze navigation and according to prediction of the upcoming pose of the virtual camera controlled by the user. Sectors are selected according the selected sectorization and the current direction and field of view and only patches encoded in regions of the atlas associated with these sectors are accessed to generate the viewport image representative of the content seen from the current point of view.

Abstract: An exemplary image processing system first writes normal line information and color information into the G buffer and depth information into the depth buffer for a first object. Next, at a time of writing the normal line information into the G buffer for a second object, the exemplary image processing system calculates a difference between the depth information of a first object and the depth information of the second object, and blends the normal line information of the first object with the normal line information of the second object based on the difference, and writes the blended normal line information into the G buffer. The exemplary image processing system then renders an image in a frame buffer based on information stored in the G buffer and light source information.

Abstract: A computer-implemented method is disclosed. The method includes: obtaining, via a first computing device, video data of a first product review video for a product; identifying a portion of the first product review video depicting the product; extracting surface textures of the product based on the identified portion of the first product review video; obtaining a first three-dimensional representation of the product; and generating an updated three-dimensional representation of the product based on the extracted surface textures and the first three-dimensional representation.

Abstract: A method includes obtaining images of an environment captured by imaging sensors associated with a passthrough AR device and position data and depth data associated with the images. The method also includes generating a point cloud representative of the environment based on the images, position data, and depth data. The method further includes generating a mesh for a specified image. The mesh includes grid points at intersections of mesh lines. The method also includes determining one or more depths of one or more grid points of the mesh. The method further includes transforming the mesh from a viewpoint of a specified imaging sensor that captured the specified image to a user viewpoint of the passthrough AR device based on the depth(s) of the grid point(s). In addition, the method includes rendering a virtual view of the specified image for presentation by the passthrough AR device based on the transformed mesh.

Abstract: Aspects of the subject disclosure may include, for example, a device having a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations of: receiving a request from a first user of an electronic event to invoke a surrogate to control an avatar of the first user; retrieving data describing characteristics of the surrogate; and altering a presentation of the avatar for the first user made to a second user, wherein the data describing characteristics of the surrogate is used to alter the presentation of the avatar. Other embodiments are disclosed.

Abstract: In some embodiments, a system generates a map of a care facility. The system comprises one or more sensors coupled to a computing device and configured to generate sensor data corresponding to locations inside the care facility. The computing device is configured to: determine, for the locations, features of the care facility based on the sensor data; and generate, based on the features, the map of the care facility that includes the locations.

Abstract: Methods and systems for establishing dental occlusion are described herein. These systems and methods can be used for 1-, 2-, or 3-piece maxillary orthognathic surgeries. An example computer-implemented method includes receiving a maxillary dental model and a mandibular dental model, identifying a plurality of dental landmarks in each of the maxillary and mandibular dental models, and extracting a plurality of points-of-interest from each of the maxillary and mandibular dental models. The dental landmarks include a plurality of maxillary dental landmarks and a plurality of mandibular dental landmarks. The method further includes aligning the maxillary and mandibular points-of-interest, and fine tuning the alignment of the maxillary and mandibular dental models to achieve maximum contact with a collision constraint.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify digital images via scene-based editing using image understanding facilitated by artificial intelligence. For example, in one or more embodiments the disclosed systems utilize generative machine learning models to create modified digital images portraying human subjects. In particular, the disclosed systems generate modified digital images by performing infill modifications to complete a digital image or human inpainting for portions of a digital image that portrays a human. Moreover, in some embodiments, the disclosed systems perform reposing of subjects portrayed within a digital image to generate modified digital images. In addition, the disclosed systems in some embodiments perform facial expression transfer and facial expression animations to generate modified digital images or animations.

Abstract: A process is provided for usage-pattern-based generation of a digital model of a product. The process includes obtaining a usage pattern of a user of a product, where the usage pattern includes a set of usage pattern parameters. In addition, the process includes using a machine learning model of an artificial intelligence system to generate a 3-D virtual image of the product aligned with the usage pattern, and analyzing, by the artificial intelligence system, the 3-D virtual image of the product to facilitate identifying a requirement specification for the product based on the usage pattern. Further, the process includes generating a digital model of a new product for the user based on the identified requirement specification.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify digital images via multi-layered scene completion techniques facilitated by artificial intelligence. For instance, in some embodiments, the disclosed systems receive a digital image portraying a first object and a second object against a background, where the first object occludes a portion of the second object. Additionally, the disclosed systems pre-process the digital image to generate a first content fill for the portion of the second object occluded by the first object and a second content fill for a portion of the background occluded by the second object. After pre-processing, the disclosed systems detect one or more user interactions to move or delete the first object from the digital image. The disclosed systems further modify the digital image by moving or deleting the first object and exposing the first content fill for the portion of the second object.

Abstract: Embodiments are generally directed to a flexible overlapping display. An embodiment of a mobile device includes a processor to process data for the mobile device, a bendable and foldable display screen, one or more device sensors to sense an orientation of the mobile device, and one or more display sensors to sense a current arrangement of the display screen. The processor is to identify one or more portions of the display screen that are visible to a user based at least in part on data from the one or more device sensors and the one or more display sensors.

Abstract: This disclosure addresses the unresolved problems of tackling object disambiguation task for an embodied agent. The embodiments of present disclosure provide a method and system for disambiguation of referred objects for embodied agents. With a phrase-to-graph network disclosed in the system of the present disclosure, any natural language object description indicating the object disambiguation task can be converted into a semantic graph representation. This not only provides a formal representation of the referred object and object instances but also helps to find an ambiguity in disambiguating the referred object using a real-time multi-view aggregation algorithm. The real-time multi-view aggregation algorithm processes multiple observations from an environment and finds the unique instances of the referred object.

Abstract: Methods, systems, and apparatus for processing point clouds using neural networks to perform a machine learning task. In one aspect, a system comprises one or more computers configured to obtain a set of point clouds captured by one or more sensors. Each point cloud includes a respective plurality of three-dimensional points. The one or more computers assign the three-dimensional points to respective voxels in a voxel grid, where the grid of voxels includes non-empty voxels to which one or more points are assigned and empty voxels to which no points are assigned. For each non-empty voxel, the one or more computers generate initial features based on the points that are assigned to the non-empty voxel. The one or more computers generate multi-scale features of the voxel grid, and the one or more computers generate an output for a point cloud processing task using the multi-scale features of the voxel grid.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify digital images using an intelligent user interface tool that determines the intent of a user interaction. For instance, in some embodiments, the disclosed systems receive, via a graphical user interface of a client device, a user interaction with a set of pixels within a digital image. The disclosed systems determine, based on the user interaction, a user intent for targeting one or more portions of the digital image for deletion, the one or more portions including an additional set of pixels that differs from the set of pixels. Based on the user intent, the disclosed systems modify the digital image to delete the one or more portions from the digital image.

Abstract: A propagating signal is propagated through a propagating medium to a plurality of receivers coupled to the propagating medium. A signal affected by a disturbance of the propagating medium is received. The received signal includes a signal portion that corresponds to the propagating signal that has been disturbed by the disturbance. At least a portion of a version of the signal portion of the received signal that corresponds to the propagating signal that has been disturbed by the disturbance is compared with one or more reference signal signatures of one or more disturbance types. Based at least in part on the comparison, it is determined that one of the one or more disturbance types corresponds to the disturbance of propagating medium.

Abstract: One common robotic task is the rearrangement of physical objects situated in an environment. This typically involves a robot manipulator picking up a target object and placing the target object in some target location, such as a shelf, cabinet or cubby, and requires the skills of picking, placing and generating complex collision-free motions, oftentimes in a cluttered environment. The present disclosure provides collision detection for object rearrangement using a three-dimensional (3D) scene representation.

Abstract: This application discloses a method and apparatus for obtaining a virtual image, a computer device, a computer-readable storage medium, and a computer program product, belonging to the technical field of artificial intelligence. The method includes obtaining a target image generation model by fusing a first image generation model and a second image generation model, the first image generation model being trained based on a sample original image, the sample original image retaining object ontology features of a sample object, and the second image generation model being trained based on a sample virtual image having target attributes; and obtaining a target virtual image corresponding to an original image of a target object based on the target image generation model, the target virtual image retaining object ontology features of the target object and having the target attributes.

Abstract: A system is disclosed for processing and streaming real-time graphics by a video-server for synchronized output via secondary-network connected display adapters to multiple displays arranged as a video-wall. This system enables the video-server to leverage performance advantages afforded by advanced GPUs, combined with low-cost Smart displays or System-on-Chip devices to deliver advanced realtime video-wall capabilities over the network while offering flexibility in the selection of network display adapters and still achieving synchronized output of multiple sub-image streams to selected end-point displays. This has applications generally in the field of real-time multiple-display graphics distribution as well as specific applications in the field of network video-walls. A method and computer readable medium are also disclosed that operate in accordance with the system.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify digital images via scene-based editing using image understanding facilitated by artificial intelligence. For instance, in one or more embodiments, the disclosed systems generate utilizing a segmentation neural network, an object mask for each object of a plurality of objects of a digital image. The disclosed systems detect a first user interaction with an object in the digital image displayed via a graphical user interface. The disclosed systems surface, via the graphical user interface, the object mask for the object in response to the first user interaction. The disclosed systems perform an object-aware modification of the digital image in response to a second user interaction with the object mask for the object.

Abstract: Systems and methods of the present disclosure are directed to a method that can include obtaining a 3D mesh comprising polygons and texture/shading data. The method can include rasterizing the 3D mesh to obtain a 2D raster comprising pixels and coordinates respectively associated with a subset of pixels. The method can include determining an initial color value for the subset of pixels based on the coordinates of the pixel and the associated shading/texture data. The method can include constructing a splat at the coordinates of a respective pixel. The method can include determining an updated color value for a respective pixel based on a weighting of the subset of splats to generate a 2D rendering of the 3D mesh based on the coordinates of a pixel and a splat.