2D to 3D Conversion via Edge-Based Depth Map Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current 3D display technologies require multiple 2D images from different viewpoints to create a 3D image, limiting the commercialization of 3D content and the ability to convert single viewpoint 2D images into stereoscopic 3D images.
Innovation Solution
A method and apparatus for generating a depth map that converts 2D images into 3D by creating an edge map, extracting edges with specific characteristics, mapping them to a line map, and generating a depth map with sequential depth orders, which can be applied to various display devices like stereoscopic 3D TVs and players.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple 2D images from different viewpoints are used to create 3D images, then 3D display quality is improved, but content production complexity and cost increase
Solution Approach 1:
The patent extracts depth information from a single 2D image by detecting edges and calculating depth maps, separating the depth component from the original 2D image. This allows 3D conversion without requiring multiple viewpoint images, thus reducing content production complexity while maintaining 3D display quality.
Solution Approach 2:
The patent creates a synthetic depth map that copies and infers depth information from the single 2D image's edge characteristics. By generating artificial depth data based on edge detection and line mapping, the system replicates the effect of multiple viewpoint images without actually requiring them.
2Device complexity
If single viewpoint 2D images are converted to 3D, then content production is simplified, but 3D image quality deteriorates
Solution Approach 1:
The patent performs preliminary edge detection and line mapping on the single 2D image before generating the depth map. By pre-processing the image to extract edge information and establish a line map, the system prepares depth information that can be used to generate high-quality 3D images despite starting from a single viewpoint.
Solution Approach 2:
The patent transforms the single 2D image into a 3D depth map by adding depth dimension information. Through edge detection, line mapping, and depth order assignment, the system converts 2D spatial information into 3D depth information, enabling 3D display from a single viewpoint image.
3Productivity
If depth map generation uses edge detection and line mapping, then processing speed increases, but depth map precision decreases
Solution Approach 1:
The patent segments the depth map generation process into distinct stages: edge detection, line mapping, and depth order assignment. By dividing the complex task into manageable segments, the system can process images faster while maintaining precision through careful execution of each segment. The line map serves as an intermediate structure that organizes edge information into precise depth layers.
Data Source
AI summary
A conversion method and apparatus with a generating of a depth map for two dimensional (2D)-to-three dimensional (3D) conversion. A depth order may be restored based on a line tracing and an edge map generated from an input image, and a stereo image may be generated using depth information.