4:4:4 Video Coding with ACT and LMCS for Better Compression
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video coding technologies face challenges in efficiently encoding and decoding high-fidelity video data in 4:4:4 chroma format due to inherent redundancies, which affect compression efficiency, particularly in applications requiring sharp edge preservation.
Innovation Solution
Implementing adaptive color-space transform (ACT) with luma mapping and chroma scaling (LMCS) to decode video data by applying inverse ACT and inverse luma mapping to convert residuals from a transformed color space to the original color space, and using block differential pulse coded modulation (BDPCM) for chroma components.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If video data is encoded in 4:4:4 chroma format to preserve color information fidelity, then image quality is improved, but compression efficiency deteriorates due to increased data redundancy
Solution Approach 1:
The patent transforms video data from the conventional YCbCr color space to the YCgCo color space through a linear transformation. This parameter change in the color space representation exploits different statistical properties of the transformed components, enabling more effective compression while preserving the full 4:4:4 chroma format color fidelity. The transformation is defined by specific matrix operations that redistribute the information across different color components.
2Productivity
If adaptive color-space transform (ACT) is applied to exploit correlations among color components, then compression performance is improved, but computational complexity increases
Solution Approach 1:
The patent applies a fixed linear transformation from YCbCr to YCgCo color space, which is computationally more efficient than adaptive methods. This parameter transformation exploits inherent correlations among color components through a predetermined mathematical relationship, achieving compression performance improvement without the computational overhead of adaptive algorithms. The transformation uses simple matrix multiplication with constant coefficients.
3Measurement precision
If video resolution is increased from high definition to 4K or 8K, then image quality is improved, but data volume and encoding complexity increase exponentially
Solution Approach 1:
The patent employs a color space transformation that prepares video data for more efficient compression at high resolutions. By transforming to YCgCo color space before compression, the method exploits statistical properties that become more pronounced at higher resolutions, enabling better compression ratios for 4K and 8K content without proportionally increasing encoding complexity.
Data Source
AI summary
An electronic apparatus performs a method of decoding video data, including receiving, from bitstream, a first syntax element in a slice header of a slice that indicates whether luma mapping with chroma scaling (LMCS) is applied to a coding unit in the slice; receiving a second syntax element for the coding unit that indicates whether the coding unit has been coded using adaptive color-space transform (ACT); if the second syntax element has a non-zero value, decoding the coding unit by applying inverse ACT to convert luma and chroma residuals of the coding unit from a transformed color space to an original color space of the video data; and if the first syntax element has a non-zero value, decoding the coding unit by performing inverse luma mapping to the luma samples and inverse scaling to the chroma residuals of the coding unit after performing the inverse ACT.