Pixel Compression Predictor Selection for Faster Lossless Encoding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data compression techniques for pixel information face challenges in achieving optimal compression ratios and efficiency, particularly in balancing compute resources, power consumption, and accuracy between lossless and lossy compression methods.
Innovation Solution
The approach involves determining the most suitable lossless or lossy compression technique for a given block of pixels by evaluating multiple predictors in parallel, selecting the technique that provides the smallest compression size, and dynamically adjusting bit widths and using bias to optimize compression ratios, while falling back to lossy compression if lossless techniques cannot meet a target output size.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If lossless compression techniques are used to preserve data accuracy, then data fidelity is improved, but compression ratio and processing speed deteriorate
Solution Approach 1:
The patent implements dynamic selection among multiple compression techniques (e.g., PNG, JPEG, WebP) based on real-time evaluation of compression ratios and processing speeds. The system adapts the compression approach for different image blocks or regions, switching between lossless and lossy methods to optimize both fidelity and speed according to specific data characteristics.
Solution Approach 2:
The system varies compression parameters such as quality thresholds, bit depths, and algorithmic settings to balance fidelity and speed. By adjusting these parameters dynamically based on image content analysis, the system achieves optimal compression performance without sacrificing necessary data accuracy.
2Productivity
If multiple compression techniques are evaluated in parallel to select the optimal method, then compression ratio is improved, but compute resources and device complexity increase
Solution Approach 1:
The patent divides the compression evaluation process into segments where different techniques are applied to different image regions or blocks. Instead of evaluating all techniques on the entire image, the system segments the work to reduce per-evaluation compute resources while maintaining overall optimization through selective application of the best-performing techniques.
Solution Approach 2:
The system performs partial evaluation of compression techniques by assessing only critical metrics (such as initial compression ratio estimates) rather than full decompression and reconstruction validation. This partial action approach reduces compute resources required for technique selection while still identifying optimal compression methods efficiently.
3Productivity
If lossy compression is used to achieve smaller file sizes, then compression ratio is improved, but data accuracy deteriorates
Solution Approach 1:
The patent applies different compression methods to different regions of the image based on local quality requirements. Critical regions (such as edges, text, or important features) are compressed using lossless or high-fidelity lossy techniques, while less critical regions use more aggressive lossy compression. This local differentiation maintains data accuracy where needed while achieving better overall compression ratios.
Solution Approach 2:
The system incorporates feedback mechanisms that evaluate the quality impact of lossy compression in real-time. By monitoring distortion metrics and comparing against threshold values, the system adjusts compression aggressiveness dynamically, ensuring data accuracy is maintained within acceptable boundaries while maximizing compression ratios.
Data Source
AI summary
Techniques are disclosed relating to data compression. In some embodiments, compression circuitry determines, at least partially in parallel for multiple different lossless compression techniques, amounts of data needed to represent, using a given lossless compression technique of the multiple lossless compression techniques, individual pixels in a set of pixels being compressed. The compression techniques may include neighbor, origin, and gradient techniques, for example. The compression circuitry may select one of the compression techniques based on comparison, among the compression techniques, of sums of: the determined amount of data for an individual pixel for a given lossless compression technique and compression metadata size for a given lossless compression technique. The compression circuitry may generate and store information that encodes values for the set of pixels using the selected compression technique.