3D Generative Design from 2D Sketching

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for converting two-dimensional conceptual designs into three-dimensional CAD models often result in discrepancies between the designer's vision and the final engineering model, leading to wasted design hours and inefficiencies.

Innovation Solution

A computer-implemented method that receives input for two-dimensional sketch elements and design relationships, generating a three-dimensional model that links these elements based on identified relationships, allowing for iterative design modifications to achieve both structural soundness and aesthetic appeal.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a second party manually converts two-dimensional conceptual designs into three-dimensional CAD models, then structural elements and engineering constraints can be evaluated, but the CAD model may differ from the designer's vision, leading to wasted design time

Engineering Contradiction:
Improvestructural integrityVSAvoiddesign time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system enables designers to automatically generate three-dimensional CAD models with structural elements directly from their two-dimensional conceptual sketches using AI algorithms. The designer's own design intent is preserved while the system automatically adds appropriate structural connections, eliminating the need for manual conversion by a second party and preventing loss of design vision.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The manual mechanical process of converting 2D sketches to 3D models by a second party is replaced with an automated computational system using machine learning algorithms. The system analyzes the designer's sketch, identifies intended structural relationships, and automatically generates the three-dimensional model with appropriate structural elements, substituting human manual work with intelligent automation.

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

2Adaptability or versatility

If designers exclude structural connections in conceptual designs to simplify the design process, then design flexibility and emphasis on key features are improved, but the design cannot be directly converted into a buildable engineering model

Engineering Contradiction:
Improvedesign flexibilityVSAvoidconvertibility to engineering model
Core Design Contradiction:
Adaptability or versatilityVSEase of manufacture

Solution Approach 1:

The system performs preliminary action by automatically analyzing the designer's conceptual sketch and predicting the intended structural connections before the design is finalized. The AI algorithm infers structural relationships from the visual information in the sketch, allowing the design to progress from conceptual to engineering-ready stage without requiring the designer to manually add structural details that would reduce flexibility.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The AI-based conversion system acts as an intermediary between the designer's conceptual sketch and the engineering model. It translates the designer's visual intent into structural connections, bridging the gap between conceptual design flexibility and engineering model requirements without requiring the designer to compromise either.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If multiple CAD models are generated to satisfy engineering constraints, then structural requirements are met, but the original design vision may be lost and design work must be repeated

Engineering Contradiction:
Improveengineering constraints satisfactionVSAvoiddesign fidelity
Core Design Contradiction:
ReliabilityVSManufacturing precision

Solution Approach 1:

The system incorporates feedback mechanisms where the AI algorithm continuously refines the generated CAD model by comparing it against both the original design sketch and engineering constraints. The system learns from the designer's corrections and adjustments, progressively improving the model to simultaneously satisfy structural requirements and preserve the original design vision, eliminating the need to generate multiple alternative models.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS11113865B2Three-dimensional generative design based on two-dimensional sketching
Publication Date: 2021.09.07 AUTODESK INC
  • US11113865B2 patent drawing
  • US11113865B2 patent drawing
  • US11113865B2 patent drawing

AI summary

One embodiment of the present invention provides a technique for generating a three-dimensional model from a two-dimensional sketch. The technique includes receiving input indicating a set of points defining a first sketch element and a second set of points defining a second sketch element included in a sketch. The technique further includes identifying one or more design relationships between the first sketch element and the second sketch element. The technique further includes generating a computer model of the sketch that represents a structure linking the first sketch element and the second sketch element according to the one or more design relationships. The technique further includes outputting the first sketch element, the second sketch element, and the structure for display.