<samp>

# CADSketchNet - An Annotated Sketch dataset for 3D CAD Model Retrieval with Deep Neural Networks
	
</samp>

<div align="center">

<span> <a href="bharadwaj-manda.github.io/">Bharadwaj Manda</a></span>,
<span> <a href="https://www.linkedin.com/in/shubham-dhayarkar-a16a75153/?originalSubdomain=in">Shubham Dhayarkar</a></span>,
<span> <a href="https://smj007.github.io/">Sai Mitheran</a></span>,
<span> <a href="https://vkviekash-homepage.github.io/">Viekash V K</a></span>,
<span> <a href="https://ed.iitm.ac.in/~raman/">Ramanathan Muthuganapathy</a></span>

	
</div>

---

[Project Page](https://bharadwaj-manda.github.io/CADSketchNet/)


This dataset is licensed under CC BY-NC-SA: Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International
This license is one of the Creative Commons licenses and allows users to share the dataset only if they (1) give credit to the copyright holder, (2) do not use the dataset for any commercial purposes, and (3) distribute any additions, transformations or changes to the dataset under this same license.

This is the repository for the 'CADSketchNet' Dataset, associated with the paper ["CADSketchNet - An Annotated Sketch dataset for 3D CAD Model Retrieval with Deep Neural Networks"](https://www.sciencedirect.com/science/article/pii/S0097849321001333). The paper is accepted for publication in the Special Section on [3DOR2021 - 14th EG 3D Object Retrieval Workshop](https://3dor2021.github.io/index.html) of the [Computers & Graphics](https://www.journals.elsevier.com/computers-and-graphics) Journal. The arxiv version of the paper is available [here](https://arxiv.org/pdf/2107.06212.pdf). The final published version of the paper is [here](https://www.sciencedirect.com/science/article/pii/S0097849321001333).

- The CADSketchNet dataset 
	- Dataset-A has 58,696 computer-generated sketches of the 3D CAD models across 68 categories of [MCB](https://mechanical-components.herokuapp.com/)
	- Dataset-B has 801 hand-drawn sketches of the 3D CAD models across 42 categories of [ESB](https://engineering.purdue.edu/cdesign/wp/downloads/)

- *Few images from the Dataset-A (computer-generated sketches) have some missing lines and features. We are currently in the process of cleaning up these sketches. An updated version will be released soon.*

For further details, contact Bharadwaj Manda via [here](https://www.linkedin.com/in/bharadwaj-manda-9730ab114/) or [here](https://bharadwaj-manda.netlify.app/)

## Download

Download the Dataset-A [here](https://drive.google.com/file/d/1kH6Bpt6IWIEOZxcu1vVBK9Bd9WG84kTk/view?usp=sharing)
- Click [here](https://drive.google.com/file/d/1ZUaO4iKDTjz7j9LDSNW8_qpFpqHpDil2/view?usp=sharing) to download the 80-20 train-test split used in the paper

Download the Dataset-B [here](https://drive.google.com/file/d/10XRLO7T58Lq54YtL7wX3CJ1VpsFUo2nW/view?usp=sharing)


## To cite this Dataset or Paper:

- Use the bibtex below:

```bibtex
@article{MANDA2021100,
title = {‘CADSketchNet’ - An Annotated Sketch dataset for 3D CAD Model Retrieval with Deep Neural Networks},
journal = {Computers & Graphics},
volume = {99},
pages = {100-113},
year = {2021},
issn = {0097-8493},
doi = {https://doi.org/10.1016/j.cag.2021.07.001},
url = {https://www.sciencedirect.com/science/article/pii/S0097849321001333},
author = {Bharadwaj Manda and Shubham Dhayarkar and Sai Mitheran and V.K. Viekash and Ramanathan Muthuganapathy},
keywords = {Retrieval, Search, Dataset, Deep Learning, CAD, Sketch}
}
```

- Or use the plain text below

---

Bharadwaj Manda, Shubham Dhayarkar, Sai Mitheran, V.K. Viekash, Ramanathan Muthuganapathy,
‘CADSketchNet’ - An Annotated Sketch dataset for 3D CAD Model Retrieval with Deep Neural Networks,
Computers & Graphics,
Volume 99, 2021,
Pages 100-113, ISSN 0097-8493,
https://doi.org/10.1016/j.cag.2021.07.001.
(https://www.sciencedirect.com/science/article/pii/S0097849321001333)

---

*Thanks are due to the many volunteers who have contributed to the dataset.*