Stereoscopic Image Generation from 2D Content via Depth Mesh Mapping

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for generating 3D imagery require capturing or rendering scenes from multiple perspectives, limiting the ability to create quality 3D imagery from scenes not originally imaged in this manner.

Innovation Solution

A computer-implemented process that generates stereoscopic images by obtaining image data with associated direction and depth values, creating a mesh displaced by these values, and mapping the data to produce stereoscopic images from different perspectives, which can be displayed to create the illusion of depth without requiring true 3D imagery capture or rendering.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If multiple perspective captures or rendering are used to produce 3D imagery, then the quality and realism of 3D imagery is improved, but the complexity and cost of the imaging system increases

Engineering Contradiction:
Improve3D imagery qualityVSAvoidimaging system complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent creates a copy of the 2D image data and uses computational algorithms to generate synthetic 3D views from this copied data. Instead of requiring multiple physical cameras, the system copies the original image data and processes it to simulate multiple perspectives, thereby reducing device complexity while maintaining 3D imagery quality.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent transforms 2D image data into 3D visual representations by adding a depth dimension through computational processing. By mapping 2D coordinates to 3D spatial coordinates and synthesizing intermediate views, the system achieves 3D imagery quality without requiring complex multi-perspective capture equipment.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Manufacturing precision

If scenes are captured from multiple perspectives using 3D cameras, then true 3D imagery is obtained, but the adaptability to work with existing 2D content is reduced

Engineering Contradiction:
Improve3D imagery qualityVSAvoidcompatibility with existing content
Core Design Contradiction:
Manufacturing precisionVSAdaptability or versatility

Solution Approach 1:

Instead of capturing 3D imagery directly with multiple cameras as traditional methods do, this patent inverts the approach by starting with existing 2D images and computationally generating 3D views from them. This allows the system to work with any existing 2D content while producing 3D imagery, thereby improving adaptability without sacrificing 3D quality.

Inventive Principle:
Principle #13The other way round (Inversion)

Solution Approach 2:

The patent creates a universal system that can process both newly captured 2D images and existing 2D content from various sources. The computational framework is designed to handle diverse input formats and generate 3D imagery consistently, making the system adaptable to work with any existing content while maintaining 3D imagery quality.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Manufacturing precision

If 3D cameras with multiple lenses are used to capture live scenes, then stereoscopic images are obtained, but the ease of operation and accessibility are reduced

Engineering Contradiction:
Improvestereoscopic image qualityVSAvoidsystem accessibility
Core Design Contradiction:
Manufacturing precisionVSEase of operation

Solution Approach 1:

The patent replaces the mechanical system of multiple physical cameras and lenses with a computational system that processes 2D images algorithmically. This substitution eliminates the need for complex hardware setups, making the system easier to operate and more accessible while maintaining stereoscopic image quality through software-based 3D view synthesis.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP3057316B1Generation of three-dimensional imagery to supplement existing content
Publication Date: 2020.04.22 DREAMWORKS ANIMATION LLC
  • EP3057316B1 patent drawingFigure 1
  • EP3057316B1 patent drawingFigure 2
  • EP3057316B1 patent drawingFigure 3A~3B

AI summary

A computer-implemented process for generating stereoscopic images to supplement existing content includes obtaining first image data and obtaining second image data comprising a plurality of sample points. A direction, a color value, and a depth value are associated with each sample point. The direction and depth values are relative to a common origin. A mesh is generated such that the mesh is displaced from the origin in the directions associated with the sample points by distances representative of the corresponding depth values. The second image data is mapped to the mesh such that the color values associated with the sample points are mapped to the mesh at the corresponding directions. First and second stereoscopic images of the mesh are generated from first and second perspectives, respectively. The first image data is caused to be displayed on a first portion of a display. At least part of both the first stereoscopic image and the second stereoscopic image is caused to be displayed on a second portion of the display. At least part of the second portion of the display does not overlap the first portion of the display.