Neural Face Identification in a 2D Wireframe Projection of a Manifold Object
Authors:
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1612-1621
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 handcrafted 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. The project page is at https://manycore-research.github.io/faceformer.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- A new algorithm for finding faces in wireframesComputer-Aided Design, 2010
- Evolutionary Search for Faces from Line DrawingsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- SMARTPAPER: An Interactive and User Friendly Sketching SystemComputer Graphics Forum, 2004
- Identifying faces in a 2D line drawing representing a manifold objectIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Long Short-Term MemoryNeural Computation, 1997
- Classification of Sketch Strokes and Corner Detection Using Conic Sections and Adaptive ClusteringJournal of Mechanical Design, 1997
- Identification of faces in a 2D line drawing projection of a wireframe objectIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996
- Automated conversion of curvilinear wire-frame models to surface boundary models; a topological approachACM SIGGRAPH Computer Graphics, 1986
- Efficiently identifying the faces of a solidComputers & Graphics, 1983
- Creating volume models from edge-vertex graphsACM SIGGRAPH Computer Graphics, 1982