CN-121996185-A - Artificial Intelligence (AI) aided split rendering

CN121996185ACN 121996185 ACN121996185 ACN 121996185ACN-121996185-A

Abstract

The present disclosure relates to Artificial Intelligence (AI) assisted split rendering. A method performed by a split rendering client on a user device is provided. The method includes establishing a split rendering session for rendering a scene, wherein objects in the scene are to be rendered by a split rendering server on a network device. In this regard, the scene will be displayed by the user device at least at a first quality level. The method includes receiving, from the split rendering server, rendered media generated by the split rendering server from objects rendered at a lower second quality level. The method includes inputting the rendered media into a Machine Learning (ML) model to restore the rendered media to at least a first quality level. And, the method includes synthesizing for display a view of the scene, wherein the view of the scene includes rendered media of at least a first quality level.

Inventors

T. Biatic
L. A. Irola
HE XUAN
G. K. Irashi

Assignees

诺基亚技术有限公司

Dates

Publication Date: 20260508
Application Date: 20251106
Priority Date: 20241108

Claims (10)

1. An apparatus for implementing a split rendering client on a user device, the apparatus comprising: At least one memory configured to store instructions, and At least one processing circuitry configured to access the at least one memory and execute the instructions to cause the apparatus at least to: establishing a split rendering session for rendering a scene, wherein objects in the scene are to be rendered by a split rendering server on a network device, wherein the scene is to be displayed by the user device at least at a first quality level; receiving, from the split rendering server, rendered media generated by the split rendering server from the object rendered at a second quality level, wherein the second quality level is lower than the first quality level; Inputting the rendered media into a Machine Learning (ML) model to restore the rendered media to at least the first quality level, and A view of the scene is synthesized for display, wherein the view of the scene includes at least the rendered media of the first quality level.
2. The apparatus of claim 1, wherein the apparatus is further caused to at least: acquiring control information for rendering the object, and Transmitting the control information to the split rendering server, and Wherein the rendered media is generated by the split rendering server from the object rendered at the second quality level based on the control information, or Wherein the rendered media received from the split rendering server is encoded rendered media and the at least one processing circuitry is configured to execute the instructions to cause the apparatus to further decode the encoded rendered media into decoded rendered media, and Wherein the apparatus being caused to input the rendered media into the ML model comprises the apparatus being caused to input the decoded rendered media into the ML model, or Wherein the apparatus being caused to receive the rendered media comprises the apparatus being caused to receive the rendered media and metadata related to the rendered media, and Wherein the apparatus being caused to input the rendered media into the ML model includes the apparatus being caused to input the rendered media and the metadata into the ML model to restore the rendered media to at least the first quality level.
3. The apparatus of claim 1, wherein the apparatus is caused to input the rendered media into the ML model comprises the apparatus being caused to perform reasoning using the ML model to restore the rendered media to at least the first quality level, and wherein the reasoning comprises one or more computations performed by an AI accelerator on the user device.
4. The apparatus of claim 3, wherein the apparatus being caused to establish the split rendering session comprises the apparatus being caused to negotiate a complexity of the reasoning supported by the split rendering client with the split rendering server, and Wherein the object is rendered by the split rendering server based on the complexity of the reasoning supported by the split rendering client, and Wherein the rendered media received from the split rendering server is decoded by decoder circuitry, wherein the apparatus is caused to establish the split rendering session comprises the apparatus being caused to negotiate decoding information with the split rendering server that is opened by the decoder circuitry, and Wherein a version of the ML model at the split rendering server is trained based on the decoding information opened by the decoder circuitry.
5. The apparatus of claim 1, wherein the at least one processing circuitry is configured to execute the instructions to cause the apparatus to further at least: Receiving an update from the split rendering server to be applied to the ML model, and The update is applied to the ML model to create an updated ML model.
6. The apparatus of claim 5, wherein the update to be applied to the ML model is received with the rendering media, and Wherein the apparatus being caused to input the rendered media into the ML model comprises the apparatus being caused to input the rendered media into the updated ML model, or Wherein the update is applied to the ML model to create the updated ML model after the rendered media is input into the ML model to recover the rendered media.
7. An apparatus for implementing a split rendering server on a network device, the apparatus comprising: At least one memory configured to store instructions, and At least one processing circuitry configured to access the at least one memory and execute the instructions to cause the apparatus at least to: Establishing a split rendering session for rendering a scene, wherein objects in the scene are to be rendered by the split rendering server, wherein the scene is to be displayed by a user device at least at a first quality level; Rendering the object at a second quality level to produce rendered media, wherein the second quality level is lower than the first quality level; Sending the rendered media to a split rendering client on the user device, at which the rendered media is to be input into a Machine Learning (ML) model to restore the rendered media to at least the first quality level; performing an update of the ML model based on the rendered media; generating an update to be applied to the ML model based on the rendered media, and The update is sent to the split rendering client, where the update is to be applied to the ML model to create an updated ML model.
8. The apparatus of claim 7, wherein the at least one processing circuitry is configured to execute the instructions to cause the apparatus to further receive control information from the split rendering client for rendering the object, and Wherein the object is rendered at the second quality level based on the control information, or Wherein the at least one processing circuitry is configured to execute the instructions to cause the apparatus to further encode the rendered media as encoded rendered media, and Wherein the apparatus being caused to send the rendered media comprises the apparatus being caused to send the encoded rendered media to the split rendering client where the encoded rendered media is to be decoded into decoded rendered media and the decoded rendered media is to be input into the ML model, or Wherein metadata related to rendered media is sent with the rendered media to the split rendering client on the user device, at which the rendered media and the metadata are to be applied to the ML model to recover the rendered media, and Wherein the updating of the ML model is performed based on the rendered media, and metadata associated with the rendered media, or Wherein the at least one processing circuitry is configured to execute the instructions to cause the apparatus to further determine the second quality level such that the ML model is capable of increasing the quality level of the rendered media by at least a quality gap between the second quality level and the first quality level.
9. The device of claim 7, wherein the split rendering client is to perform reasoning using the ML model to restore the rendered media to at least the first quality level, and Wherein the apparatus being caused to establish the split rendering session includes the apparatus being caused to negotiate with the split rendering client a complexity of the reasoning supported by the split rendering client, and Wherein the object is rendered based on the complexity of the reasoning supported by the split rendering client.
10. The apparatus of claim 7, wherein the apparatus being caused to perform the updating of the ML model comprises the apparatus being caused to: generating an update to be applied to the ML model based on the rendered media, and Sending the update to the split rendering client, at which the update is applied to the ML model to create an updated ML model; wherein the update to be applied to the ML model is sent to the split rendering client with the rendering media and the rendering media is input into the updated ML model, and Wherein after the rendered media is input into the ML model to recover the rendered media, the update is sent to the split rendering client where the update is applied to the ML model to create the updated ML model.

Description

Artificial Intelligence (AI) aided split rendering Technical Field The present disclosure relates generally to telecommunications and, in particular, to split graphics rendering in a telecommunications system. Background A telecommunication system may be regarded as a facility that enables communication sessions between two or more entities, such as user terminals, base stations and/or other nodes, by providing carriers between the various entities involved in the communication path. For example, a telecommunication system may be provided by means of a communication network and one or more compatible communication devices. For example, a communication session may include communications for carrying data for the communication, such as voice, video, electronic mail (email), text messages, multimedia and/or content data, and the like. Non-limiting examples of services provided include two-way or multi-way calls, data communication or multimedia services, and access to data network systems such as the internet. In a wireless telecommunication system, at least part of a communication session between at least two stations occurs over a wireless link. Examples of wireless systems include Public Land Mobile Networks (PLMNs), satellite-based communication systems, and different wireless local area networks (e.g., wireless Local Area Networks (WLANs)). Some wireless systems may be divided into cells and are therefore generally referred to as cellular systems. The user may access the telecommunication system by means of a suitable communication device or terminal. The communication device of a user may be referred to as a User Equipment (UE) or user equipment. The communication device is provided with suitable signal receiving and transmitting means for enabling communication, e.g. enabling access to a communication network or communication directly with other users. A communication device may access a carrier provided by a station (e.g., a base station of a cell) and transmit and/or receive communications on the carrier. The telecommunications system and associated devices generally operate in accordance with a given standard or specification which sets out what the various entities associated with the system are permitted to do and how that should be achieved. Communication protocols and/or parameters which should be used for the connection are also generally defined. One example of a telecommunication system is the Universal Mobile Telecommunication System (UMTS). Other examples of telecommunication systems are Long Term Evolution (LTE), LTE-advanced, and so-called 5G or New Radio (NR) networks. NR is being standardized by the third generation partnership project (3 GPP). Disclosure of Invention Example implementations of the present disclosure relate to split graphics rendering in telecommunications, and in particular, in telecommunications systems. For purposes of illustration, the present disclosure includes, but is not limited to, the following example implementations. Some example implementations provide an apparatus implementing a split rendering client on a user device, the apparatus comprising at least one memory configured to store instructions, and at least one processing circuitry configured to access the at least one memory and execute the instructions, such that the apparatus at least establishes a split rendering session for rendering a scene, wherein objects in the scene are to be rendered by a split rendering server on a network device, wherein the scene is to be displayed by the user device at least at a first quality level, receives rendering media from the split rendering server generated by the split rendering server from objects rendered at a second quality level, wherein the second quality level is lower than the first quality level, inputs the rendering media into a Machine Learning (ML) model to restore the rendering media to the at least first quality level, and synthesizes a view of the scene for display, wherein the view of the scene comprises the rendering media at the at least first quality level. Some example implementations provide a method performed by a split rendering client on a user device, the method comprising establishing a split rendering session for rendering a scene, wherein objects in the scene are to be rendered by a split rendering server on a network device, wherein the scene is to be displayed by the user device at least at a first quality level, receiving, from the split rendering server, rendered media generated by the split rendering server from objects rendered at a second quality level, wherein the second quality level is lower than the first quality level, inputting the rendered media into a Machine Learning (ML) model to restore the rendered media to at least the first quality level, and synthesizing a view of the scene for display, wherein the view of the scene comprises the rendered media at least the first quality level. Some example implementations provide a