Video Decoding Tile Loop Filtering Parallelization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional video encoding devices face challenges in parallelizing the encoding and decoding processes due to interdependence between coding units, particularly at tile boundaries, which hinders efficient loop filtering across tiles.
Innovation Solution
A video decoding device and method that separates encoded bit data into tiles, allowing for independent prediction difference decoding and filtering processes within each tile, enabling parallel loop filtering across tiles using tile decoders and filters with specific filter parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the entire screen is processed as a single unit for loop filtering, then filtering quality is maintained, but parallel processing capability is lost
Solution Approach 1:
The image is divided into multiple tiles, and loop filtering is performed independently on each tile using tile-specific filter parameters. This segmentation enables parallel processing of different tiles while maintaining filtering quality through localized parameter optimization for each tile region.
2Loss of time
If loop filtering is performed on the entire screen after all tiles are decoded, then filtering consistency is achieved, but processing time increases
Solution Approach 1:
The loop filtering process is segmented into tile-level independent operations, allowing simultaneous filtering of multiple tiles rather than sequential processing of the entire screen, thereby reducing total processing time while maintaining consistency through standardized filter parameter application.
Solution Approach 2:
Filter parameters are determined and prepared for each tile before the actual filtering operation. This preliminary preparation enables immediate execution of filtering as soon as tile decoding is complete, eliminating waiting time while ensuring consistent parameter application across all tiles.
3Speed
If tile-based parallel processing is implemented, then processing speed improves, but inter-tile reference dependencies increase complexity
Solution Approach 1:
The filter parameter determination process is extracted from the global screen-level operation and assigned to individual tile-level operations. Each tile independently determines and applies its own filter parameters, eliminating the need for complex inter-tile reference management while enabling straightforward parallel processing.
Data Source
AI summary
A parallel processing starting unit 3 that partitions an inputted image into tiles each having a predetermined size, and distributes tiles obtained through the partitioning, and N tile encoding units 5-1 to 5-N each of that carries out a prediction difference encoding process on a tile distributed thereto by the parallel processing starting unit 3 to generate a local decoded image are disposed, and each of N tile loop filter units 7-1 to 7-N determines a filter per tile suitable for a filtering process on the local decoded image generated by the corresponding one of the tile encoding units 5-1 to 5-N, and carries out the filtering process on the local decoded image by using the filter.