Neural Network Based Reconstruction of a 3D Object from a 2D Wireframe

TL;DR

This paper introduces a neural network and genetic algorithm-based system that automatically reconstructs 3D objects from 2D wireframes, mimicking human ability to interpret 2D sketches into 3D models.

Contribution

It presents a novel automated approach combining neural networks and genetic algorithms for 3D reconstruction from 2D wireframes, advancing computational sketch understanding.

Findings

Successfully reconstructs 3D models from 2D wireframes

Demonstrates robustness across various wireframe complexities

Outperforms previous methods in accuracy and automation

Abstract

We propose a new approach for constructing a 3D representation from a 2D wireframe drawing. A drawing is simply a parallel projection of a 3D object onto a 2D surface; humans are able to recreate mental 3D models from 2D representations very easily, yet the process is very difficult to emulate computationally. We hypothesize that our ability to perform this construction relies on the angles in the 2D scene, among other geometric properties. Being able to reproduce this reconstruction process automatically would allow for efficient and robust 3D sketch interfaces. Our research focuses on the relationship between 2D geometry observable in the sketch and 3D geometry derived from a potential 3D construction. We present a fully automated system that constructs 3D representations from 2D wireframes using a neural network in conjunction with a genetic search algorithm.