Entropy Encoding with Interval-Based Latent Scaling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing adaptive quantization and latent scaling technologies in data coding, such as those used in JPEG AI, suffer from high computational complexity while maintaining coding performance.
Innovation Solution
Implement a method that sets non-overlapping threshold intervals for scaling features and probability distribution parameters, reducing the need for repeated scaling operations and thereby lowering algorithm complexity without compromising coding performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If adaptive quantization technology and latent scaling technology are used to improve coding performance, then coding performance is improved, but computational complexity increases
Solution Approach 1:
The feature map is divided into multiple non-overlapping intervals based on threshold values. Each interval corresponds to a specific scaling factor range. By segmenting the feature map into discrete intervals, the continuous scaling process is transformed into a discrete selection process, reducing computational complexity while maintaining coding performance.
Solution Approach 2:
The patent changes the parameter representation by introducing interval-based threshold values that categorize scaling factors into discrete ranges. Instead of using continuous scaling factors, the system uses interval thresholds to determine which scaling factor to apply, transforming a complex continuous parameter into a simplified discrete parameter system.
2Manufacturing precision
If multiple scaling operations are performed to maintain coding performance, then coding performance is maintained, but algorithm complexity increases
Solution Approach 1:
The feature map is divided into multiple non-overlapping intervals based on threshold values. Each interval corresponds to a specific scaling factor range. By segmenting the feature map into discrete intervals, the continuous scaling process is transformed into a discrete selection process, reducing computational complexity while maintaining coding performance.
Solution Approach 2:
The intervals and threshold values are pre-defined and prepared before the actual scaling operation. By establishing the interval structure in advance, the system avoids performing multiple overlapping scaling operations during execution, instead simply selecting the appropriate pre-defined interval and applying its corresponding scaling factor.
Data Source
AI summary
An encoding and decoding method and apparatus are provided. The method includes: obtaining a feature map of a to-be-encoded picture; obtaining a probability distribution parameter map of the feature map; obtaining a first matrix based on the probability distribution parameter map; determining, from a plurality of intervals, a first interval corresponding to the first matrix, where the plurality of intervals do not overlap each other, and each interval corresponds to at least one scaling factor; scaling, based on a first scaling factor corresponding to the first interval, the feature map and the probability distribution parameter map that correspond to the first matrix, to obtain a scaled probability distribution parameter map; and performing entropy encoding on a scaled feature map based on the scaled probability distribution parameter map, and writing an entropy encoding result into a bitstream.