Abstract: An example method for communicating AI data from a sender device to a receiver device in a computing environment may include generating protocol instances of AI data; generating AI metadata description based on AI model information; sending a request comprising the AI metadata description to a receiver device for establishing a session; establishing a session by receiving a response from the receiver device based on the request; sending the AI data associated with the AI metadata description, to the receiver device based on the established session. The receiver device may receive the request and determine the compatibility of the metadata description, generate and send a response, followed by receiving the AI data associated with the AI metadata description.

Abstract: Systems and methods for optimal split federated learning (O-SFL) in a wireless network, including: receiving, by a federal device in the wireless network, local split points associated with a deep neural network (DNN) model over a time period from at least one client device of a plurality of client devices, wherein the plurality of client devices are connected to an edge device for training the DNN model using split federated learning (SFL); determining, by the federal device, an average of the local split points; determining, by the federal device, a global split point for partitioning the DNN model between the at least one client device and the edge device based on the average of the local split points; and applying, by the federal device, the determined global split point to train the DNN model.

Abstract: The present disclosure relates to methods and devices for managing communication of Artificial Intelligence (AI) data between devices in a computing environment. Detecting one or more sets of changes in data values associated with current data frame based on comparison between current data frame and previously generated data frame. Further, performing generation of one or more data chunks of an updated data frame, comprising one or more data segments based on the one or more sets of changes, based on one of, a first codec technique and second codec technique. Transmitting one or more data chunks to one or more receiver devices based on the respective data chunk satisfying a specified chunk size. Transmitting the one or more data chunks generated for updated data frame to one or more receiver devices based on respective data chunk satisfying a specified chunk size.

Abstract: A method for deferred rendering on an extended reality (XR) device includes establishing a transport session for content on the XR device with a server. The method also includes performing a loop configuration for the content based on the transport session between the XR device and the server. The method further includes providing pose information based on parameters of the loop configuration to the server. The method also includes receiving pre-rendered content based on the pose information from the server. In addition, the method includes processing and displaying the pre-rendered content on the XR device.

Abstract: Provided is a method for adaptively streaming an artificial intelligence (AI) model file, including determining a capability of a first electronic device and a capability of a second electronic device, network information associated with the first and second electronic devices, and AI model information associated with the AI model file; determining to adaptively stream the AI model file based on the determined capabilities and information; pre-processing the AI model file; and adaptively streaming the AI model.

Abstract: A method of accessing 3D media content based on perspective-based random access is provided. The method includes receiving the media content and metadata, wherein the metadata includes first information about a perspective and second information about at least one face onto which the 3D object is projected, and the at least one face is associated with the perspective, and performing the perspective-based random access for the media content based on the first information and the second information.

Abstract: A method of accessing 3D media content based on perspective-based random access is provided. The method includes receiving the media content and metadata, wherein the metadata includes first information about a perspective and second information about at least one face onto which the 3D object is projected, and the at least one face is associated with the perspective, and performing the perspective-based random access for the media content based on the first information and the second information.

Abstract: An encoding device, a decoding device and a method for point cloud encoding is provided. The method includes generating, for a 3D point cloud, frames corresponding to attributes of the 3D point cloud and an occupancy map. The method also includes encoding, the frames to generate one or more bitstreams. The one or more bitstreams include individual tracks and media content. The individual tracks include media tracks and a timed metadata track. The timed metadata track references the media tracks and the media tracks correspond respectively to the attributes. The method also includes generating a container including the one or more bitstreams transmitting the container.

Abstract: An encoding device, a decoding device and a method for point cloud encoding is provided. The method includes generating, for a 3D point cloud, frames corresponding to attributes of the 3D point cloud and an occupancy map. The method also includes encoding, the frames to generate one or more bitstreams. The one or more bitstreams include individual tracks and media content. The individual tracks include media tracks and a timed metadata track. The timed metadata track references the media tracks and the media tracks correspond respectively to the attributes. The method also includes generating a container including the one or more bitstreams transmitting the container.