Visual Quality Assessment Using Game State Data for Cloud Gaming
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing visual quality assessment models are inadequate for gaming content, particularly in cloud-based streaming, as they fail to differentiate between intentional and unintentional image degradation effects such as blurriness and blockiness.
Innovation Solution
A visual quality assessment method and system that incorporates supplementary inputs from game state data, including texture information, polygon count, game engine data, post-processing data, and input device data, to adjust quality assessment scores and account for intentional image effects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional visual quality assessment models (PSNR, SSIM, VMAF) are used for gaming content, then the assessment process is simple and fast, but the accuracy is poor because they cannot differentiate between intentional and unintentional image degradation
Solution Approach 1:
The patent introduces game state data as an intermediary element that mediates between the image quality assessment and the final quality score. This supplementary information acts as a mediator that helps distinguish between intentional graphical effects and actual quality degradation, thereby improving measurement precision without requiring fundamental changes to the assessment methodology
Solution Approach 2:
The patent modifies the quality assessment by incorporating additional parameters (game state data including texture information, polygon counts, post-processing effects) alongside traditional image quality metrics. This parameter enrichment allows the system to adjust quality scores based on contextual understanding of gaming content, improving accuracy while maintaining a structured assessment framework
2Reliability
If traditional quality metrics are applied to gaming content, then computational resources are saved, but the quality scores are misleading due to inability to account for intentional graphical effects
Solution Approach 1:
The patent applies preliminary action by obtaining and analyzing game state data before performing the final quality assessment. By preparing and incorporating contextual information about intentional graphical effects in advance, the system can make more reliable quality determinations without requiring excessive computational resources during the actual assessment process
Solution Approach 2:
The patent implements feedback mechanisms where game state information feeds into the quality assessment process, allowing the system to adjust and refine quality scores based on contextual understanding. This feedback loop improves reliability by continuously incorporating relevant information about intentional graphical effects while maintaining efficient resource utilization
Data Source
Figure 1~2
AI summary
A visual quality assessment 'VQA' method comprises the steps of, for all or part of an image, obtaining data indicative of an intended graphical state of the image or corresponding part thereof, from a device generating the image; and performing a VQA based on the image or corresponding part thereof, wherein at least one calculation step of the VQA is modified responsive to the obtained data.