3D Model Generation from 2D Images via Automatic Point Mapping

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional techniques for generating three-dimensional models are unintuitive, require advanced skills, and are limited by the need for specialized knowledge and expensive machinery, making them inaccessible to users without extensive expertise.

Innovation Solution

A system that generates three-dimensional models from two-dimensional images by allowing users to specify points on different views of an object, using image processing to estimate corresponding points and create a mesh, enabling intuitive and efficient model creation without requiring advanced knowledge of complex tools or machinery.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If conventional 3D model generation techniques are used, then manufacturing precision can be achieved, but device complexity and ease of operation deteriorate due to complicated user interfaces and specialized knowledge requirements

Engineering Contradiction:

Improve3D model accuracyVSAvoiduser interface complexity

Core Design Contradiction:

Manufacturing precisionVSEase of operation

Solution Approach 1:

The system uses 2D image copies of the object from multiple views to generate the 3D model, replacing the need for complex scanning machinery. Users simply provide 2D images, and the system automatically processes them into a 3D representation, eliminating complicated user interfaces while maintaining model accuracy

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent replaces mechanical 3D scanning systems with an image-processing-based approach. Instead of using physical scanners and complex mechanical interfaces, the system uses computational algorithms to generate 3D models from 2D images, significantly simplifying the user interaction process

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Manufacturing precision

If conventional 3D scanning machinery is used, then 3D model generation is achieved, but device complexity and cost increase due to expensive specialized equipment

Engineering Contradiction:

Improve3D model qualityVSAvoidscanning machinery requirements

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system creates 3D models by processing copies of 2D images rather than requiring physical 3D scanning equipment. This approach replaces expensive specialized machinery with standard image processing capabilities, reducing device complexity while maintaining model quality

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent uses inexpensive 2D images as input material instead of requiring expensive 3D scanning equipment. The 2D images serve as disposable input that can be easily obtained and replaced, eliminating the need for costly specialized machinery

Inventive Principle:

Principle #27Cheap short-living objects (Disposable)

3Ease of operation

If sculpting techniques are used, then intuitive model creation is improved, but productivity deteriorates due to time-consuming manual manipulation

Engineering Contradiction:

ImproveintuitivenessVSAvoidmodel creation speed

Core Design Contradiction:

Ease of operationVSProductivity

Solution Approach 1:

The system performs preliminary actions by automatically generating the 3D model structure from 2D images before user interaction. The computationally intensive mesh generation and point mapping are completed automatically, allowing users to work with pre-processed models rather than manually creating them from scratch

Inventive Principle:

Principle #10Preliminary action

4Ease of operation

If simple shape manipulation is used, then ease of operation is improved, but manufacturing precision deteriorates due to limitations in creating complex objects

Engineering Contradiction:

Improveinterface simplicityVSAvoidobject detail accuracy

Core Design Contradiction:

Ease of operationVSManufacturing precision

Solution Approach 1:

The patent transitions from 2D image inputs to 3D model outputs by adding a dimensional transformation step. The system processes 2D images through computational algorithms that infer and construct 3D spatial relationships, enabling accurate representation of complex objects while keeping the user interface simple

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS10318102B23D model generation from 2D images

Publication Date: 2019.06.11 ADOBE INC

AI summary

Techniques and systems are described to generate a three-dimensional model from two-dimensional images. A plurality of inputs is received, formed through user interaction with a user interface. Each of the plurality of inputs define a respective user-specified point on the object in a respective one of the plurality of images. A plurality of estimated points on the object are generated automatically and without user intervention. Each of the plurality of estimated points corresponds to a respective user-specified point for other ones of the plurality of images. The plurality of estimated points is displayed for the other ones of the plurality of images in the user interface by a computing device. A mesh of the three-dimensional model of the object is generated by the computing device by mapping respective ones of the user-specified points to respective ones of the estimated points in the plurality of images.