3D Reconstruction from 2D Concept Drawings via Normal Vector Fields
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods fail to effectively characterize and generate three-dimensional information from two-dimensional concept drawings, which are crucial for conveying the three-dimensional appearance of objects.
Innovation Solution
A method involving computers to analyze cross-hairs in concept drawings, defining orthogonal cross-section planes and tangent vectors, and performing constrained optimization to generate a normal vector field that represents the object's surface, allowing for the propagation of surface normal vectors to populate the three-dimensional space.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If conventional methods are used to represent three-dimensional objects, then two-dimensional drawings can be created, but the three-dimensional information is lost or insufficient
Solution Approach 1:
The patent applies dimensionality change by extracting three-dimensional normal vector fields from two-dimensional concept drawings. The system analyzes 2D boundary curves and cross-sections to infer 3D surface geometry, transforming planar visual information into spatial characteristics that preserve depth and form data.
Solution Approach 2:
The patent introduces normal vector fields as an intermediary representation between the 2D concept drawing and the 3D object. These vector fields serve as a mathematical mediator that encodes surface orientation and curvature information, enabling accurate 3D reconstruction without requiring complex direct modeling.
2Measurement precision
If detailed three-dimensional characterization is performed, then accuracy of object representation improves, but computational complexity increases
Solution Approach 1:
The patent segments the concept drawing into distinct geometric elements: boundary curves defining object contours and cross-sections revealing internal structure. By processing these segmented components separately and combining their contributions, the system achieves accurate 3D characterization while managing computational complexity through modular analysis.
Data Source
AI summary
Methods for characterizing two-dimensional concept drawings are disclosed. The concept drawings comprise cross-sections intersecting at cross-hairs. The method comprises: determining, for each cross-section: a plane on which the cross-section is located, the plane having a normal vector in a three-dimensional coordinate system; and, for each cross-hair on the cross-section, a tangent vector in the three-dimensional coordinate system which is tangent to the cross-section at the cross-hair. For each cross-hair comprising ith and jth intersecting cross-sections, one or more constraints are satisfied, the constraints comprising: the normal vector ni of the plane on which the ith cross-section is located is at least approximately orthogonal to the normal vector nj of the plane on which the jth cross-section is located; and the tangent vector tij to the ith cross-section at the cross-hair is at least approximately orthogonal to the tangent vector tji to the jth cross-section at the cross-hair.