Abstract: Systems and methods provide a provisioning framework for a distributed graphics processing unit (GPU) service. A network device in a network receives, from an application, a service request for multi-access edge compute (MEC)-based virtual graphic processing unit (vGPU) services. The network device receives real-time utilization data from multiple MEC clusters in different MEC network locations and generates a utilization view of the multiple MEC clusters in the different MEC network locations. The network device selects, based on the real-time utilization view, one of the different MEC network locations to provide the vGPU services and instructs a of the multiple MEC clusters in the one of the different MEC network locations to perform container provisioning and service provisioning for the vGPU services.

Abstract: This disclosure relates generally to method and system for draping a 3D garment on a 3D human body. Dressing digital humans in 3D have gained much attention due to its use in online shopping and draping 3D garments over the 3D human body has immense applications in virtual try-on, animations, and accurate fitment of the 3D garment is the utmost importance. The proposed disclosure is a single unified garment deformation model that learns the shared space of variations for a body shape, a body pose, and a styling garment. The method receives a plurality of human body inputs to construct a 3D skinned garments for the subject. The deep draper network trained using a plurality of losses provides efficient deep neural network based method that predicts fast and accurate 3D garment images. The method couples the geometric and multi-view perceptual constraints that efficiently learn the garment deformation's high-frequency geometry.

Abstract: Systems and techniques are provided for registering three-dimensional (3D) images to deformable models.

Abstract: A depth image is used to obtain a three dimensional (3D) geometry of an object as an object mesh. The object mesh is obtained using an object shell representation. The object shell representation is based on a series of depth images denoting the entry and exit points on the object surface that camera rays would pass through. Given a set of entry points in the form of a masked depth image of an object, an object shell (an entry image and an exit image) is generated. Since entry and exit images contain neighborhood information given by pixel adjacency, the entry and exit images provide partial meshes of the object which are stitched together in linear time using the contours of the entry and exit images. A complete object mesh is provided in the camera coordinate frame.

Abstract: A method and a device for displaying clothing patterns determine attributes of bounding volumes for each body part, to which a body type and an orientation of a 3D avatar are reflected, based on locations of feature points extracted from data of the 3D avatar, determine initial locations of the clothing patterns by placing arrangement points on the bounding volumes depending on the attributes of the bounding volumes for each body part, and drape the clothing patterns to the 3D avatar depending on the initial locations.

Abstract: Provided are a design assistance device, a design assistance system, a server, and a design assistance method that displays shapes and specification information of plural items included in an item group so that a user can easily view the items. The design assistance device includes: a three-dimensional data acquisition unit that acquires three-dimensional data of an item group including a plurality of items; a display data generation unit that generates two-dimensional display data including a two-dimensional display representing an appearance of the item group and specification information of at least one of the items in one observation direction in the three-dimensional data; and a display mode determination unit that determines a display mode of the specification information in the two-dimensional display based on a shape of each of the items as well as relative positions and relative orientations between the items as viewed in the one observation direction.

Abstract: A sensor simulation system may generate sensor data for use in simulations by rendering two-dimensional views of a three-dimensional simulated environment. In various examples, the sensor simulation system uses sensor dependency data to determine specific views to be re-rendered at different times during the simulation. The sensor simulation system also may generate unified views with multi-sensor data at each region (e.g., pixel) of the two-dimensional view for consumption by different sensor types. A hybrid technique may be used in some implementations in which rasterization is used to generate a view, after which ray tracing is used to align the view with a particular sensor. Spatial and temporal upsampling techniques also may be used, including depth-aware and velocity-aware analyses for simulated objects, to improve view resolution and reduce the frequency of re-rendering views.

Abstract: A method and apparatus for outputting a three-dimensional (3D) image are provided. To output a 3D image, a stereo image is generated based on viewpoints of a user and rendered into a 3D image. Since the stereo image is generated based on the viewpoints of the user, the user views a different side of an object appearing in the 3D image depending on a viewpoint of the user.

Abstract: An extended reality (XR) system includes an extended reality application executing on a processor within the XR system. The XR system receives, via a client device, a selection of an extended reality (XR) object located within an XR environment. The XR system receives, via the client device, a request to move the selected XR object within the XR environment. The XR system calculates a first distance between a first feature of the XR object and a first plane associated with a first physical object within the XR environment. The XR system determines that the first distance is within a particular distance. In response to determining that the first distance is within the particular distance, the XR system positions the first feature within the XR environment such that the first feature is coplanar with the first plane.

Abstract: Disclosed herein are various embodiments for image editing and sharing in an augmented reality computing environment. An embodiment operates by receiving, from a first user, an edit command indicating a selection of an image from within an augmented reality computing environment. Responsive to the edit command, the image is moved from a first location within the augmented reality computing environment to a second location within the augmented reality computing environment closer to the first user than the first location. One or more edits to the image are received from the first user. The image including the one more edits are returned to the first location upon a completion of the one or more edits.

Abstract: Systems and methods for generating synthetic video are disclosed. For example, a system may include a memory unit and a processor configured to execute the instructions to perform operations. The operations may include receiving video data, normalizing image frames, generating difference images, and generating an image sequence generator model. The operations may include training an autoencoder model using difference images, the autoencoder comprising an encoder model and a decoder model. The operations may include identifying a seed image frame and generating a seed difference image from the seed image frame. The operations may include generating, by the image sequence generator model, synthetic difference images based on the seed difference image. In some aspects, the operations may include using the decoder model to synthetic normalized image frames from the synthetic difference images. The operations may include generating synthetic video by adding background to the synthetic normalized image frames.

Abstract: Systems, methods, and computer program products are described that include obtaining, at a processor, a first image from an image capture device onboard a computing device, detecting, using the processor and at least one sensor, a device orientation of the computing device associated with capture of the first image, determining, based on the device orientation and a tracking stack associated with the computing device, a rotation angle in which to rotate the first image, rotating the first image to the rotation angle to generate a second image, and generating neural network based estimates associated with the first image and the second image.

Abstract: In an embodiment, a system provides object tracking and 6D pose estimations to a robot that performs different tasks such as manipulation and navigation. In an embodiment the 6D object pose is determined using a Rao-Blackwellized particle filtering framework, where the 3-D rotation and the 3-D translation of the object is decoupled. In an embodiment, the system provides the 3-D translation of an object along with a full distribution over the 3-D rotation. In an embodiment, the 3-D rotation is determined by discretizing the rotation space, and training an autoencoder network to construct a codebook of feature embeddings for the discretized rotations. In an embodiment, the system is able to track objects with arbitrary symmetries while also maintaining adequate posterior distributions.

Abstract: A method of managing access to a physical memory formed of n memory page frames using a set of virtual address spaces having n virtual address spaces each formed of a plurality p of contiguous memory pages. The method includes receiving a write request to write a block of data to a virtual address within a virtual address space i of the n virtual address spaces, the virtual address defined by the virtual address space i, a memory page j within that virtual address space i and an offset from the start of that memory page j; translating the virtual address to an address of the physical memory using a virtual memory table having n by p entries specifying mappings between memory pages of the virtual address spaces and memory page frames of the physical memory, wherein the physical memory address is defined by: (i) the memory page frame mapped to the memory page j as specified by the virtual memory table, and (ii) the offset of the virtual address; and writing the block of data to the physical memory address.

Abstract: An apparatus for crash performance prediction of a vehicle includes: a data processor configured to generate a test target overlap image by pre-processing test target design data; and an output device configured to output at least one of a predicted impact value and a predicted impact rating value for an input of the test target overlap image based on a crash performance prediction model by machine learning the existing overlap image of pre-processed existing design data and the existing impulse data corresponding to the existing design data.

Abstract: The mesh tracking described herein involves mesh tracking on 3D face models. In contrast to existing mesh tracking algorithms which generally require user intervention and manipulation, the mesh tracking algorithm is fully automatic once a template mesh is provided. In addition, an eye and mouth boundary detection algorithm is able to better reconstruct the shape of eyes and mouths.

Abstract: A method for enabling the enhanced user-to-user communication in digital realities comprising generating a marker of a target user that is persistently applied on the target user; detecting, through a wireless network, the presence of a target user device and counterpart user device connected to the server via the wireless network; sending a notification to the counterpart user device informing about the presence of the target user device based on a set of rules; receiving one or more forms of interaction from the counterpart user device on the marker of the target user; opening up a communication channel between the counterpart user device and target user device; and receiving, processing and accordingly redirecting corresponding communications through and between the counterpart user device and target user device. A system thereof is also disclosed.

Abstract: A computer application method for generating a three-dimensional (3D) face model is provided, performed by a face model generation model running on a computer device, the method including: obtaining a two-dimensional (2D) face image as input to the face model generation model; extracting global features and local features of the 2D face image; obtaining a 3D face model parameter based on the global features and the local features; and outputting a 3D face model corresponding to the 2D face image based on the 3D face model parameter.

Abstract: A method for generating a three-dimensional working surface of a human body includes receiving input data corresponding to images; generating a first point cloud from the input data, each point being associated with a three-dimensional spatial coordinate; determining a plurality of attributes at each point of the first point cloud, calculating a set of geometric parameters from a regression carried out from a series of matrix operations performed according to different layers of a neural network trained from a plurality of partial views of parametric models parameterised with different parameterisation configurations; determining a parameterised model to generate a body model of a body including a first meshing.

Abstract: A computer-implemented method of augmented reality includes capturing the video flux with a video camera, extracting, from the video flux, one or more 2D images each representing the real object, and obtaining a 3D model representing the real object. The method also includes determining a pose of the 3D model relative to the video flux, among candidate poses. The determining rewards a mutual information, for at least one 2D image and for each given candidate pose, which represents a mutual dependence between a virtual 2D rendering and the at least one 2D image. The method also includes augmenting the video flux based on the pose. This forms an improved solution of augmented reality for augmenting a video flux of a real scene including a real object.