Image Decoder Cache Padding for Reduced Cloud Gaming Latency

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In cloud gaming scenarios, the decoding capability of user terminals is limited, leading to significant delays and lagging due to the decoding frame cache of video hardware.

Innovation Solution

An image processing method and apparatus that inserts padding frames between decoded image frames in a cache queue, ensuring the target image frame is at the first position, thereby improving decoding efficiency and reducing time delays.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of time

If video frames are decoded sequentially using traditional decoding methods, then decoding completeness is ensured, but time delay increases and processing smoothness deteriorates

Engineering Contradiction:
Improvedecoding time delayVSAvoidprocessing smoothness
Core Design Contradiction:
Loss of timeVSProductivity

Solution Approach 1:

The patent applies preliminary action by inserting padding frames before actual video content frames into the decoding queue in advance. This allows the decoder to pre-process and buffer data structures, reducing the time delay when actual content frames need to be decoded and displayed, thereby improving processing smoothness without compromising decoding completeness.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent uses padding frames as intermediary elements between the decoder and actual video content. These padding frames act as mediators that occupy queue positions and trigger premature decoding operations, allowing the system to reduce time delay by processing content frames earlier than traditional sequential decoding would permit.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Loss of time

If padding frames are inserted into the cache queue, then decoding time delay is reduced, but device complexity increases

Engineering Contradiction:
Improvedecoding time delayVSAvoiddecoding system complexity
Core Design Contradiction:
Loss of timeVSDevice complexity

Solution Approach 1:

The patent changes the parameter of frame insertion position in the decoding queue, specifically inserting padding frames at calculated positions before actual content frames. This parameter change enables time delay reduction through strategic positioning without requiring fundamental changes to the decoding architecture, thus limiting the increase in device complexity.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent uses padding frames as disposable, temporary objects that serve their purpose of reducing time delay and are then discarded. These padding frames are simple data structures with minimal processing requirements, allowing the system to reduce time delay without significant increases in device complexity.

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

3Productivity

If padding frames are inserted between target image frame and next image frame, then processing smoothness is improved, but data structure complexity increases

Engineering Contradiction:
Improveprocessing smoothnessVSAvoiddata structure complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the video frame sequence by inserting padding frames between target image frames and next image frames. This segmentation creates distinct processing zones in the decoding queue, allowing the system to improve processing smoothness by controlling the timing and order of frame decoding without creating overly complex data structures.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent uses padding frames as simplified copies or placeholders that replicate the basic frame structure without containing actual video content. These copied structures enable the system to improve processing smoothness by maintaining consistent data formats while avoiding the complexity of managing diverse frame types and structures.

Inventive Principle:
Principle #26Copying

Data Source

PatentEP4044608B1Image processing method and apparatus, electronic device and storage medium
Publication Date: 2025.08.13 TENCENT TECHNOLOGY (SHENZHEN) CO LTD
  • EP4044608B1 patent drawingFigure 1a~1b
  • EP4044608B1 patent drawingFigure 2a
  • EP4044608B1 patent drawingFigure 2b

AI summary

The present application discloses an image processing method and apparatus, an electronic device and a storage medium. Said method comprises: receiving padding frame information and an image frame set of an image sequence to be processed which are sent by a server; inputting the image frame set into a cache queue of a decoder frame by frame, and determining, as a target image frame, an image frame currently located at the first position of the cache queue; inserting, on the basis of the padding frame information, a padding frame between the target image frame and the next image frame of the target image frame, so that the remaining frames, except the target image frame, in the cache queue are padding frames; when it is detected that the decoding of the target image frame is completed, taking the next image frame of the target image frame as a new target image frame, and executing the step of inserting, on the basis of the padding frame information, the padding frame between the target image frame and the next image frame of the target image frame, until all the image frames in the image frame set are decoded completely; and processing the decoded image frames, and displaying a processing result. The described solution can reduce the time delay brought by decoding the image sequence.