# Reconstructing vehicles from orthographic drawings using deep neural networks

arXiv: https://arxiv.org/abs/2206.08789 · HTML: https://mlsanity.com/paper/2206.08789/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 32 references that are in the map.
- First posted on arXiv 14 Jun 2022.

## Builds on (most cited first, 25 of 25)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Learning Implicit Fields for Generative Shape Modeling](https://mlsanity.com/paper/1812.02822/) (2018)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019)
- [AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generation](https://mlsanity.com/paper/1802.05384/) (2018)
- [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020)
- [SAL: Sign Agnostic Learning of Shapes from Raw Data](https://mlsanity.com/paper/1911.10414/) (2019)
- [ARCH: Animatable Reconstruction of Clothed Humans](https://mlsanity.com/paper/2004.04572/) (2020)
- [Learning a Multi-View Stereo Machine](https://mlsanity.com/paper/1708.05375/) (2017)
- [DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracing](https://mlsanity.com/paper/1911.13225/) (2019)
- [SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis](https://mlsanity.com/paper/1708.01749/) (2017)
- [Learning to Infer Implicit Surfaces without 3D Supervision](https://mlsanity.com/paper/1911.00767/) (2019)
- [Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era](https://mlsanity.com/paper/1906.06543/) (2019)
- [Deep 3D Capture: Geometry and Reflectance from Sparse Multi-View Images](https://mlsanity.com/paper/2003.12642/) (2020)
- [Adversarial Generation of Continuous Implicit Shape Representations](https://mlsanity.com/paper/2002.00349/) (2020)
- [3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks](https://mlsanity.com/paper/1707.06375/) (2017)
- [SurfNet: Generating 3D shape surfaces using deep residual networks](https://mlsanity.com/paper/1703.04079/) (2017)
- [Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapes](https://mlsanity.com/paper/1809.07917/) (2018)
- [MVPNet: Multi-View Point Regression Networks for 3D Object Reconstruction from A Single Image](https://mlsanity.com/paper/1811.09410/) (2018)
- [Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation](https://mlsanity.com/paper/1802.09987/) (2018)

## Abstract (arXiv)

This paper explores the current state-of-the-art of object reconstruction from multiple orthographic drawings using deep neural networks. It proposes two algorithms to extract multiple views from a single image. The paper proposes a system based on pixel-aligned implicit functions (PIFu) and develops an advanced sampling strategy to generate signed distance samples. It also compares this approach to depth map regression from multiple views. Additionally, the paper uses a novel dataset for vehicle reconstruction from the racing game Assetto Corsa, which features higher quality models than the commonly used ShapeNET dataset. The trained neural network generalizes well to real-world inputs and creates plausible and detailed reconstructions.