Depth Map Propagation Using Intermediate Maps and Motion Vectors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for propagating depth-related information from one image to another in an image sequence struggle with objects having similar texture information at different depths, leading to errors in depth map propagation.
Innovation Solution
A multi-step approach is employed to generate an intermediate depth map by propagating depth values from a first depth map to a second depth map using pixels from both images, with a motion vector calculated to correct errors and preserve edge integrity, utilizing techniques like bilateral filtering and motion estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If depth values are propagated from a first depth-map to a second depth-map using conventional methods, then the process is simple and fast, but propagation errors occur especially for objects with similar texture information at different depths
Solution Approach 1:
The patent segments the propagation process into multiple steps: generating an intermediate depth-map first, then using motion vectors to refine the final depth-map. This multi-stage segmentation allows each step to focus on specific aspects of the problem, improving overall accuracy while managing complexity through structured processing
Solution Approach 2:
The patent introduces an intermediate depth-map as a mediator between the source depth-map and the final target depth-map. This intermediate representation allows for error correction and refinement through motion vector calculation, acting as a buffer that improves propagation reliability without requiring direct complex processing between source and target
2Manufacturing precision
If motion vectors are calculated using depth values from spatial regions, then edge integrity is preserved, but the processing time and computational load increase
Solution Approach 1:
The patent performs preliminary action by generating the intermediate depth-map before calculating motion vectors. This preliminary step prepares the data structure and reduces the complexity of subsequent motion vector calculations, as the intermediate map already contains refined depth information that simplifies the matching process
Solution Approach 2:
The patent applies partial action by calculating motion vectors only for specific spatial regions around key locations in the depth-map, rather than processing the entire map uniformly. This selective approach maintains edge integrity at critical locations while reducing overall processing time and computational load
Data Source
AI summary
The present invention relates to an apparatus for and a method of propagating depth-related information from a first depth-map (810) associated with a first image (820) to a second depth-map (860) associated with a second image (830), the first and second image being temporally proximate images in an image sequence. The method comprises generating an intermediate depth-map (840) associated with the second image (830) by propagating depth values from the first depth-map (810) to the intermediate depth-map (840) using pixels of the first image (820) and the second image (830), and generating a motion vector (850) using information comprising depth values in a spatial region around a first location in the first depth-map (810) and depth values in a spatial region around a second location in the intermediate depth-map (840) and generating a depth value for the second location in the second depth-map (860) using information comprising the motion vector (850) and the first depth-map (810).