# Deep Learning Assisted Optimization for 3D Reconstruction from Single 2D Line Drawings

arXiv: https://arxiv.org/abs/2209.02692 · HTML: https://mlsanity.com/paper/2209.02692/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 63 references that are in the map.
- First posted on arXiv 6 Sep 2022.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generation](https://mlsanity.com/paper/1802.05384/) (2018)
- [ABC: A Big CAD Model Dataset For Geometric Deep Learning](https://mlsanity.com/paper/1812.06216/) (2018)
- [DeepCAD: A Deep Generative Network for Computer-Aided Design Models](https://mlsanity.com/paper/2105.09492/) (2021)
- [Computer-Aided Design as Language](https://mlsanity.com/paper/2105.02769/) (2021)
- [SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Design](https://mlsanity.com/paper/2007.08506/) (2020)
- [Vitruvion: A Generative Model of Parametric CAD Sketches](https://mlsanity.com/paper/2109.14124/) (2021)
- [Sketch2Model: View-Aware 3D Modeling from Single Free-Hand Sketches](https://mlsanity.com/paper/2105.06663/) (2021)
- [Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketches](https://mlsanity.com/paper/2104.00482/) (2021)
- [Engineering Sketch Generation for Computer-Aided Design](https://mlsanity.com/paper/2104.09621/) (2021)
- [3D Sketching using Multi-View Deep Volumetric Prediction](https://mlsanity.com/paper/1707.08390/) (2017)
- [3D Shape Reconstruction from Free-Hand Sketches](https://mlsanity.com/paper/2006.09694/) (2020)
- [Neural Face Identification in a 2D Wireframe Projection of a Manifold Object](https://mlsanity.com/paper/2203.04229/) (2022)
- [Variational B-rep Model Analysis for Direct Modeling using Geometric Perturbation](https://mlsanity.com/paper/1903.07770/) (2019)
- [A decision-support method for information inconsistency resolution in direct modeling of CAD models](https://mlsanity.com/paper/1906.08433/) (2019)

## Built on by (most cited first, 1 of 1)

- [GroundUp: Rapid Sketch-Based 3D City Massing](https://mlsanity.com/paper/2407.12739/) (2024)

## Abstract (arXiv)

In this paper, we revisit the long-standing problem of automatic reconstruction of 3D objects from single line drawings. Previous optimization-based methods can generate compact and accurate 3D models, but their success rates depend heavily on the ability to (i) identifying a sufficient set of true geometric constraints, and (ii) choosing a good initial value for the numerical optimization. In view of these challenges, we propose to train deep neural networks to detect pairwise relationships among geometric entities (i.e., edges) in the 3D object, and to predict initial depth value of the vertices. Our experiments on a large dataset of CAD models show that, by leveraging deep learning in a geometric constraint solving pipeline, the success rate of optimization-based 3D reconstruction can be significantly improved.