Adaptive Wavefront Split for Parallel Video Coding

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing video compression/decompression systems face challenges in achieving high visual quality and processing efficiency, particularly due to visual artifacts caused by wavefront split techniques used in parallel processing environments, which affect the subjective quality of compressed video.

Innovation Solution

The solution involves adaptively adjusting the location of wavefront splits in video encoding based on frame-level quantization parameters and content adaptivity, minimizing visual artifacts by varying the wavefront split location according to the frame's quantization parameter and content complexity, thereby balancing throughput and processing time while reducing noticeable defects.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If wavefront split techniques are used in parallel processing environments, then processing efficiency and hardware utilization are improved, but visual artifacts are introduced that degrade subjective video quality

Engineering Contradiction:

Improveprocessing efficiencyVSAvoidvisual artifacts

Core Design Contradiction:

ProductivityVSObject-affected harmful factors

Solution Approach 1:

The patent applies dynamics by making the wavefront split configuration adaptive rather than static. The encoder dynamically adjusts wavefront split parameters based on frame-level quantization parameters and content complexity, allowing the system to optimize between processing efficiency and visual quality for different video content and encoding conditions

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent changes parameters by introducing frame-level quantization parameter-dependent wavefront split configurations. The system varies wavefront split location, orientation, and granularity based on the quantization parameter and content complexity metrics, enabling parameter-based optimization of the trade-off between parallel processing efficiency and artifact reduction

Inventive Principle:

Principle #35Parameter changes

2Device complexity

If wavefront split location is fixed, then hardware utilization is simplified, but visual artifacts propagate across the frame degrading quality

Engineering Contradiction:

Improvewavefront split configurationVSAvoidartifact propagation

Core Design Contradiction:

Device complexityVSObject-affected harmful factors

Solution Approach 1:

The patent applies local quality by making wavefront split configuration content-adaptive. Different regions of the video frame receive different wavefront split treatments based on local content complexity metrics, allowing the system to apply stronger parallel processing where content is simple and reduce wavefront splits where content complexity makes artifacts more noticeable

Inventive Principle:

Principle #3Local quality

3Speed

If parallel processing is increased, then encoding speed is improved, but processing time for individual blocks increases due to synchronization requirements

Engineering Contradiction:

Improveencoding speedVSAvoidsynchronization overhead

Core Design Contradiction:

SpeedVSLoss of time

Solution Approach 1:

The patent applies partial action by implementing selective wavefront splitting rather than uniform parallel processing across the entire frame. The system applies parallel processing to regions where it provides benefit while maintaining sequential processing in regions where synchronization overhead would outweigh performance gains, based on content complexity analysis

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12101479B2Content and quality adaptive wavefront split for parallel video coding

Publication Date: 2024.09.24 INTEL CORP

AI summary

Techniques related to parallel block video coding using an adaptive wavefront split are discussed. Such techniques include adaptively applying a wavefront split in a video frame based on a frame level quantization parameter of the video frame, an encode duration of a previous frame, and/or image content of the video frame.