Affine Motion Compensation Bandwidth Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video coding standards face challenges in reducing bandwidth requirements for affine motion compensation due to the increased bandwidth burden caused by interpolating reference samples for sub-block motion compensation.
Innovation Solution
The proposed technique involves determining a single reference block that includes all corner sub-blocks of a current block, using their respective motion information to align corners of the single reference block with the corner sub-blocks, and retrieving data from this single reference block to predict the sub-blocks, rather than fetching individual reference samples for each sub-block.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sub-block motion compensation is used to improve prediction accuracy, then prediction precision is improved, but bandwidth consumption increases
Solution Approach 1:
The patent merges multiple reference blocks (first reference block and second reference block) into a single reference block. The single reference block contains both the first reference block corresponding to the first sub-block and the second reference block corresponding to the second sub-block. This merging reduces bandwidth consumption by avoiding the need to separately fetch and process multiple reference blocks, while still maintaining the ability to provide different motion compensation predictions for different sub-blocks.
2Measurement precision
If multiple reference blocks are fetched for different sub-blocks to maintain prediction accuracy, then prediction quality is improved, but device complexity increases
Solution Approach 1:
The patent combines multiple reference blocks into a single reference block structure. The single reference block contains both the first reference block and the second reference block, allowing the decoder to process one unified data structure rather than managing multiple separate reference blocks. This reduces processing complexity while maintaining the capability to support different motion vectors for different sub-blocks.
Data Source
AI summary
An example device for coding video data is configured to determine that a block of the video data includes a plurality of sub-blocks, each of the sub-blocks having respective motion information referring to respective reference blocks in a reference picture in a memory, determine a single reference block of the reference picture, the single reference block including each of the respective reference blocks, wherein determining the single reference block comprises: determine four corner sub-blocks of the block included in the plurality of sub-blocks; and determine the single reference block according to the respective motion information for the four corner sub-blocks such that corners of the single reference block correspond to corners of the respective reference blocks of the four corner sub-blocks, retrieve data of the single reference block from the reference picture, and predict the sub-blocks from the respective reference blocks using the data of the single reference block.