Video Decoder SAO Line Buffer Reduction via Tri-Level Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing High-Efficiency Video Coding (HEVC) decoder requires significant internal memory and hardware cost due to the need for large line buffers to store neighboring pixel data for Sample Adaptive Offset (SAO) processing across tile boundaries or LCU-row boundaries, which increases the hardware cost and reduces processing efficiency.
Innovation Solution
The proposed method reduces the required line buffer size for SAO processing by using tri-level comparison results, which are compactly represented using fewer bits, allowing for efficient storage and retrieval of data across LCU, LCU-row, and tile boundaries, thereby minimizing the hardware cost and improving processing speed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If large line buffers are used to store neighboring pixel data for SAO processing across tile boundaries or LCU-row boundaries, then the processing completeness and video quality are maintained, but the hardware cost and internal memory requirements increase significantly
Solution Approach 1:
The patent extracts only the essential comparison results (tri-level comparison: greater than, equal to, less than) needed for SAO processing, rather than storing complete neighboring pixel data. This selective extraction of critical information reduces memory requirements while maintaining processing accuracy.
Solution Approach 2:
Instead of storing raw pixel data and performing comparisons later, the patent inverts the approach by pre-computing and storing only the comparison results. This reversal of the processing sequence eliminates the need for large buffers to hold original pixel values.
2Adaptability or versatility
If large line buffers are allocated for SAO processing, then all neighboring pixel data can be stored, but the hardware cost and device complexity increase
Solution Approach 1:
The patent uses compact, temporary storage for comparison results that can be discarded after SAO processing. Instead of maintaining large persistent buffers, the system uses small, disposable storage structures that hold only the minimal necessary information for the current processing step.
Solution Approach 2:
The patent changes the data representation parameter from storing full pixel values (8 bits or more per pixel) to storing compact comparison results (2 bits per comparison: greater than, equal to, less than). This parameter transformation dramatically reduces the memory footprint.
3Measurement precision
If full-resolution pixel data is stored in line buffers, then accurate SAO processing can be performed, but the system bandwidth and processing efficiency decrease
Solution Approach 1:
The patent performs the comparison operation in advance during the deblocking filter stage, storing the results for later use in SAO processing. This preliminary computation eliminates the need to re-access and re-process full-resolution pixel data during SAO, improving processing efficiency.
Data Source
AI summary
A method and apparatus for SAO (sample adaptive offset) processing in a video decoder are disclosed. Embodiments according to the present invention reduce the required line buffer associated with the SAO processing. According to one embodiment, tri-level comparison results for one deblocked pixel row or column of the image unit are determined according to SAO type of the deblocked pixel row or column. The tri-level comparison results are stored in a buffer and the tri-level comparison results are read back from the buffer for SAO processing of the subsequent row or column from a subsequent image unit. The comparison results correspond to “larger”, “equal” and “smaller” states. The comparison results can be stored more efficiently.