XR Video Disparity Adjustment Using Depth Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual adjustment of image disparity in extended reality (XR) videos is cumbersome and inaccurate, leading to user visual fatigue due to excessive disparity between left-eye and right-eye images.
Innovation Solution
An automatic disparity adjustment method using depth maps to determine disparity adjustment parameters, including scaling factors and offsets, which are applied to XR videos to adjust disparities to a target value, thereby eliminating the need for manual adjustment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual adjustment of disparity is performed, then adjustment can be performed, but the process is cumbersome and the adjustment result is inaccurate
Solution Approach 1:
The system automatically performs disparity adjustment by acquiring depth maps, calculating depth values, and determining adjustment parameters without requiring manual user intervention. The algorithm self-adjusts the disparity parameters based on the calculated depth information, eliminating the need for cumbersome manual adjustment operations while achieving accurate results.
Solution Approach 2:
The patent replaces the manual mechanical adjustment process with an automated computational system. Instead of manual manipulation of disparity parameters, the system uses depth map acquisition, depth value calculation, and automated parameter determination algorithms to substitute the manual adjustment mechanism, thereby improving both accuracy and ease of operation.
2Object-affected harmful factors
If disparity is not adjusted, then the video can be viewed, but users experience visual fatigue due to excessive disparity
Solution Approach 1:
The system performs disparity adjustment in advance during the video recording process. Depth maps are acquired and depth values are calculated for each frame, and adjustment parameters are determined before the video is viewed. This preliminary adjustment eliminates visual fatigue factors before the user experiences the video, rather than requiring post-processing or real-time adjustment during viewing.
Solution Approach 2:
The patent introduces depth maps as an intermediary element between the raw binocular video and the final adjusted output. The depth map serves as a mediator that carries depth information, which is then used to calculate appropriate disparity adjustment parameters. This intermediary mechanism enables automatic adjustment without requiring complex direct analysis of the video content itself.
3Measurement precision
If automatic disparity adjustment is implemented, then adjustment accuracy improves, but additional processing steps are required
Solution Approach 1:
The patent merges the disparity adjustment process with the video recording process. Depth map acquisition, depth value calculation, and adjustment parameter determination are integrated into the recording workflow, so that adjustment parameters are calculated and applied during recording rather than as a separate post-processing step. This merging maintains high accuracy while improving overall processing efficiency.
Data Source
AI summary
Embodiments of the present application provide a disparity adjustment method, a device, and a storage medium. The method includes: acquiring a depth map of a current frame during a process of recording an extended reality video, wherein the current frame includes a left-eye image and a right-eye image; determining a depth value of the current frame based on the depth map of the current frame; determining disparity adjustment parameters of the current frame based on the depth value of the current frame and a target depth value, wherein the disparity adjustment parameters include a scaling factor and an offset of an image, and the disparity adjustment parameters are used to adjust a disparity of the current frame to a target disparity corresponding to the target depth value; adding the disparity adjustment parameters of the current frame to a video file of the extended reality video.