Multi-View Video Pruning Using Color Validation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increase in the number of reference view images leads to a significant increase in image data, making it difficult to efficiently process and manage, especially in immersive media services that require omnidirectional 6 DoF capabilities.
Innovation Solution
An apparatus and method that utilize color information in addition to depth values to improve the pruning process by generating a pruning mask for additional view images, revalidating the mask using color information, and detecting outliers to refine the pruning process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the number of reference view images is increased to improve immersive media service quality, then the coverage and viewing experience are improved, but the amount of image data increases significantly making it difficult to process
Solution Approach 1:
The patent extracts and removes redundant overlapping data between multiple reference views through pruning processes. By identifying and eliminating duplicate regions in the multi-view video data, the system reduces the total data quantity while preserving the essential omnidirectional viewing information, thus resolving the contradiction between comprehensive coverage and data volume.
Solution Approach 2:
The patent discards redundant overlapping portions between reference views during the pruning process, and recovers or reconstructs the complete view synthesis capability through selective retention of non-redundant data. This allows the system to maintain 6 DoF omnidirectional capability with reduced data storage and processing requirements.
2Loss of substance
If traditional pruning process is used to remove overlapping areas, then data redundancy is reduced, but the reliability of pruning is insufficient leading to potential loss of valid information
Solution Approach 1:
The patent implements a feedback mechanism where the pruning mask generation process uses color information from both the basic view and additional view to validate and refine the pruning decisions. By continuously comparing color relationships and adjusting the pruning mask based on this feedback, the system improves pruning reliability while effectively removing redundancy without losing valid information.
Solution Approach 2:
The patent changes the parameters used in the pruning process by incorporating color information (color relationship, color difference) in addition to traditional depth-based methods. This multi-parameter approach allows for more accurate discrimination between redundant and valid pixels, improving pruning reliability while maintaining effective redundancy reduction.
3Productivity
If only depth values are used in the pruning process, then the processing is simple and fast, but the pruning accuracy is insufficient
Solution Approach 1:
The patent merges multiple information sources including depth values, color information (RGB values), and color relationship metrics into a unified pruning decision process. By combining these different types of data, the system achieves both accurate pruning (improved measurement precision) and maintains processing efficiency through integrated computation rather than separate sequential operations.
Solution Approach 2:
The patent creates a composite pruning approach that combines multiple types of information (depth, color, color relationship) similar to how composite materials combine different properties. This composite method leverages the strengths of each information type to achieve both speed and accuracy in the pruning process.
Data Source
AI summary
Disclosed herein are an apparatus and method for removing redundant data between multi-view videos. The method includes generating a pruning mask of an additional view image by mapping a basic view image to the additional view image, among multi-view images, and revalidating the pruning mask using color information of the basic view image and the additional view image. Revalidating the pruning mask may include defining a color relationship between the basic view image and the additional view image by extracting predetermined sample values from corresponding pixels between the basic view image and the additional view image, which are included in the pruning candidate group of the pruning mask, and detecting pixels that do not match the defined color relationship, among the pixels in the pruning mask, as outliers.