Multi-view Video Decoding Using Pre-computed Disparity Compensation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing multi-view video coding technologies, such as MV-HEVC, face challenges in real-time decoding due to high time consumption in disparity compensation, making it impossible to decode four UHD level videos on consumer-level computers, as motion compensation and disparity compensation occupy a significant portion of the decoding time.
Innovation Solution
A decoding method that utilizes an SVM learning method to reduce time consumption for disparity compensation by generating and using a disparity compensation model trained with depth information, motion estimation, and pixel information similarity values from multi-view video data, enabling efficient block matching and disparity compensation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of substance
If disparity compensation is performed using traditional MV-HEVC methods, then multi-view video coding compression efficiency is improved, but decoding time consumption increases significantly
Solution Approach 1:
The patent pre-calculates and stores disparity compensation results in a lookup table during the encoding phase. During decoding, the system directly retrieves pre-computed disparity compensation values from the lookup table based on motion vectors and block positions, eliminating the need for real-time disparity compensation calculations and significantly reducing decoding time consumption.
Solution Approach 2:
The patent creates a copy of the reference picture and applies disparity compensation to generate a compensation picture in advance. This pre-generated compensation picture is then used during decoding without requiring real-time disparity compensation operations, thereby reducing the computational burden and time consumption during the decoding process.
2Measurement precision
If motion compensation and disparity compensation are performed for all blocks, then coding accuracy is improved, but processing complexity increases
Solution Approach 1:
The patent applies disparity compensation selectively only to blocks that require it, rather than uniformly to all blocks. By identifying and processing only the necessary blocks based on their characteristics and motion vectors, the system maintains coding accuracy where needed while reducing overall processing complexity and computational load.
Solution Approach 2:
The patent performs disparity compensation partially by using motion vectors to determine which blocks need compensation and applying it only to those specific blocks. This partial application of disparity compensation maintains necessary coding accuracy while avoiding the excessive processing complexity that would result from applying it to all blocks without distinction.
Data Source
AI summary
A decoding method of multi-view video information is provided. The decoding method of multi-view video information includes: receiving a bit stream about video data of a plurality of videos photographed by a plurality of cameras; generating first information by extracting depth information of a block in a video frame of a plurality of videos from video data included in the bit stream; generating second information by determining whether the same motion estimation is generated between video frames of the plurality of videos; generating third information by extracting pixel information of a block in the video frame of the plurality of videos; and performing block matching and disparity compensation between video frames of the plurality of videos by inputting the first information to third information to a disparity compensation model of multi-view video information which is generated by being trained in advance.