Parallel Entropy Coding Reordering for Faster Video Decoding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current entropy coding methods are inherently serial, which poses challenges for high-speed video decoding, especially for devices with limited processing power, and struggle with efficient compression due to computational demands and changing probability distributions.
Innovation Solution
A parallel processing architecture for entropy coding and decoding that reorders input sequences into groups with unique contexts, allowing each group to be processed independently and entropy encoded in parallel, followed by reordering to reconstruct the original sequence.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If serial entropy coding is used, then compression efficiency is maintained, but decoding speed is limited
Solution Approach 1:
The input sequence is divided into multiple groups based on a reordering schedule, where each group contains symbols that can be processed independently. This segmentation enables parallel processing of multiple groups simultaneously, increasing decoding speed while maintaining compression efficiency through context-adaptive coding within each group.
Solution Approach 2:
The patent introduces a temporal dimension to the encoding process by using a reordering schedule that assigns symbols to different time slots or groups. This allows the decoder to process multiple groups in parallel across different time dimensions, effectively increasing throughput without sacrificing the contextual information needed for efficient compression.
2Speed
If parallel processing is implemented, then decoding speed increases, but computational overhead increases
Solution Approach 1:
The reordering schedule is predetermined and prepared in advance, organizing symbols into groups that are ready for parallel processing. This preliminary organization eliminates the need for complex runtime decisions about which symbols to process together, reducing computational overhead while maintaining high parallel processing efficiency.
Solution Approach 2:
Each group processed in parallel maintains its own local context model and probability distributions, independent of other groups. This local quality approach allows each parallel processing unit to operate autonomously with simplified computations, reducing overall computational overhead while achieving high-speed parallel decoding.
3Measurement precision
If context modeling is performed for each symbol sequentially, then accuracy is maintained, but processing time increases
Solution Approach 1:
The sequence of symbols is segmented into multiple groups that can be processed in parallel. Each group maintains its own context modeling accuracy by considering the local sequence of symbols within that group, while the overall processing time is reduced through simultaneous processing of multiple groups.
Solution Approach 2:
The context modeling is made dynamic by adapting the reordering schedule and group assignments based on the statistical properties of the input data. This allows the system to maintain high context modeling accuracy for each group while optimizing the parallel processing configuration to minimize total processing time.
Data Source
AI summary
A method for parallel context modeling through reordering the bits of an input sequence to form groups of bits in accordance with a context model-specific reordering schedule. The reordering schedule is developed such that the groups of bits are formed to satisfy two conditions: first, that the context for each of the bits in a group of bits is different from the context of each of the other bits in that group, and the context of each of the bits in that group is determined independently from each of the other bits in that group. The parallel context modeling may be used in encoding or decoding operations.