Distributed XR Computing Optimization via Edge Node Metrics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing XR technologies face challenges in maintaining low latency and delivering a seamless user experience, especially when offloading processing to a server side, and they struggle with visual tracking, initialization, and device pose tracking on lightweight client devices.
Innovation Solution
The implementation of an improved edge node that assesses network and system metrics to optimize XR computing distribution, offloading processing functions to either the edge node or client devices based on their capabilities and network conditions, and using advanced visual feature descriptor extraction methods to reduce computational load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If full XR processing is offloaded to a centralized server, then client device computing requirements are reduced, but latency increases and processing feasibility is limited
Solution Approach 1:
The patent segments XR processing into multiple components distributed across different locations: client device (initialization, feature detection), edge node (visual tracking, pose estimation), and centralized server (rendering). This segmentation allows each component to be processed at the most appropriate location, reducing overall latency while maintaining low client device complexity.
Solution Approach 2:
The patent introduces an edge node as an intermediary between the client device and centralized server. The edge node performs visual tracking and pose estimation locally, acting as a mediator that reduces the data transmission burden and latency associated with centralized processing, while still leveraging server-side rendering capabilities.
2Loss of time
If processing functions are retained at the edge node, then latency is reduced, but edge node computing load increases
Solution Approach 1:
The patent applies local quality by performing only essential processing functions (initialization, feature detection, visual tracking) at the edge node rather than all processing. This allows the edge node to reduce its computing load by offloading rendering tasks to the centralized server, maintaining low latency for critical functions while managing edge node resource consumption.
3Quantity of substance
If simplified feature descriptor extraction is used, then data transmission bandwidth is reduced, but accuracy deteriorates due to sensitivity to sensor characteristics and lighting changes
Solution Approach 1:
The patent applies preliminary action by performing feature detection and descriptor extraction at the client device before transmission to the edge node. This preliminary processing reduces the data transmission bandwidth requirement by sending only essential feature data rather than full images, while maintaining accuracy through client-side preprocessing that accounts for device-specific characteristics.
4Measurement precision
If deep learning is applied to visual feature extraction, then accuracy is improved, but real-time performance lags compared to traditional SLAM systems
Solution Approach 1:
The patent applies partial action by using deep learning selectively for initialization and feature detection at the client device, rather than applying it to all processing stages. This allows the system to benefit from improved accuracy where deep learning provides the most value while avoiding the computational overhead that would compromise real-time performance in subsequent tracking stages.
Data Source
AI summary
Methods and systems are described for distributed extended reality (XR) computing optimization for an edge node connectable to a client device and an XR content server across a network. XR computing is apportioned to the edge node and the client device so that a wide variety of client devices, from light to heavy, are accommodated based on metrics of the edge node, the client device, the XR content server, and the network. Some of the apportionments include extraction of feature descriptors by the client device to avoid transmitting full image data from the client device to the edge node. The feature descriptors are used for tracking initialization and frame to frame tracking. Overall system performance is improved delivering an improved user experience. Related apparatuses, devices, techniques, and articles are also described.