Substitute Image Generation for Cloud Gaming Latency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In cloud gaming services and other image-based data communication scenarios, there is a risk of failing to receive image data by the time it should be displayed, especially due to server or network overload and connection instability, which can lead to delays or interruptions in image rendering.
Innovation Solution
The proposed solution involves an image display control device and method that anticipates potential data reception failures by generating substitute images based on previously received data. This is achieved through machine learning models that learn from past data to predict and generate images that can be displayed in case of data loss or corruption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If retransmission of data is started after a failure of reception of the data is confirmed, then data integrity is improved, but image display timing is delayed
Solution Approach 1:
The terminal generates substitute images in advance based on previously received image data before actual data reception failure occurs. This preliminary action ensures that when data reception fails, the substitute images are already prepared and can be displayed immediately without waiting for retransmission, thus resolving the contradiction between data reliability and display timing.
Solution Approach 2:
The terminal creates substitute images as copies or approximations of the original images using machine learning models trained on previously received image data. These substitute images serve as replacements when original image data is lost or corrupted, allowing continuous display without interruption while maintaining visual coherence.
2Duration of action of stationary object
If machine learning models are used to generate substitute images, then image display continuity is improved, but device complexity increases
Solution Approach 1:
The machine learning models are trained in advance using previously received image data, so that when data reception fails, the models are already prepared to generate substitute images. This preliminary training reduces the computational burden during actual failure scenarios, maintaining display continuity while managing device complexity.
Solution Approach 2:
The substitute images generated by the machine learning models are temporary replacements used only when data reception fails. These disposable substitute images allow the system to maintain display continuity without requiring permanent complex processing capabilities, as the substitute images are discarded once original data is received.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Provided are an image display control device, a transmitting device, an image display control method, and a program are provided. The image display control device, the transmitting device, the image display control method, and the program make it possible to reduce a risk of being unable to receive image-based data by a timing when the data should be displayed if retransmission of the data is started after a failure of reception of the data is confirmed. An upscaling section (34) generates a to-be-displayed image on the basis of image data. A substitute image generating section (38) generates a substitute image corresponding to second image data on the basis of first image data. According to success or failure of reception of the second image data, a display control section (40) causes either one of the to-be-displayed image generated on the basis of the second image data and the substitute image generated on the basis of the first image data to be displayed. The substitute image generating section (38) starts the generation of the substitute image corresponding to the second image data based on the first image data before the success or failure of the reception of the second image data is confirmed.