Neural Face Identification in a 2D Wireframe Projection of a Manifold Object

TL;DR

This paper introduces a data-driven Transformer-based approach for identifying face boundaries in 2D wireframe projections of 3D objects, improving robustness and handling complex geometries in CAD line drawings.

Contribution

It presents a novel sequence generation method for face identification in wireframes, avoiding heuristic searches and leveraging face types for better accuracy.

Findings

Effective in handling curved surfaces and nested edge loops

Reduces reliance on hand-crafted rules and heuristics

Potential for improved 3D reconstruction from 2D line drawings

Abstract

In computer-aided design (CAD) systems, 2D line drawings are commonly used to illustrate 3D object designs. To reconstruct the 3D models depicted by a single 2D line drawing, an important key is finding the edge loops in the line drawing which correspond to the actual faces of the 3D object. In this paper, we approach the classical problem of face identification from a novel data-driven point of view. We cast it as a sequence generation problem: starting from an arbitrary edge, we adopt a variant of the popular Transformer model to predict the edges associated with the same face in a natural order. This allows us to avoid searching the space of all possible edge loops with various hand-crafted rules and heuristics as most existing methods do, deal with challenging cases such as curved surfaces and nested edge loops, and leverage additional cues such as face types. We further discuss how possibly imperfect predictions can be used for 3D object reconstruction.