Article

Deep Vectorization of Technical Drawings

Authors:

Vage Egiazarian,

Alexey Artemov,

Denis Volkhonskiy,

Aleksandr Safin,

Maria Taktasheva,

Evgeny BurnaevAuthors Info & Claims

Computer Vision – ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XIII

Pages 582 - 598

https://doi.org/10.1007/978-3-030-58601-0_35

Published: 23 August 2020 Publication History

Abstract

We present a new method for vectorization of technical line drawings, such as floor plans, architectural drawings, and 2D CAD images. Our method includes (1) a deep learning-based cleaning stage to eliminate the background and imperfections in the image and fill in missing parts, (2) a transformer-based network to estimate vector primitives, and (3) optimization procedure to obtain the final primitive configurations. We train the networks on synthetic data, renderings of vector line drawings, and manually vectorized scans of line drawings. Our method quantitatively and qualitatively outperforms a number of existing techniques on a collection of representative technical drawings.

References

[1]

Open CASCADE Technology OCCT. https://www.opencascade.com/, Accessed 05 March 2005

[2]

PrecisionFloorplan. http://precisionfloorplan.com, Accessed 05 March 2020

[3]

Bessmeltsev M and Solomon J Vectorization of line drawings via polyvector fields ACM Trans. Graph. (TOG) 2019 38 1 9

Digital Library

[4]

Chai, D., Forstner, W., Lafarge, F.: Recovering line-networks in images by junction-point processes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1894–1901 (2013)

[5]

Chen J, Du M, Qin X, and Miao Y An improved topology extraction approach for vectorization of sketchy line drawings The Visual Comput. 2018 34 12 1633-1644

[6]

Chen JZ, Lei Q, Miao YW, and Peng QS Vectorization of line drawing image based on junction analysis Sci. China Inf. Sci. 2015 58 7 1-14

[7]

Chu H, Wang S, Urtasun R, and Fidler S Leibe B, Matas J, Sebe N, and Welling M HouseCraft: building houses from rental ads and street views Computer Vision – ECCV 2016 2016 Cham Springer 500-516

[8]

Delalandre M, Valveny E, Pridmore T, and Karatzas D Generation of synthetic documents for performance evaluation of symbol recognition & spotting systems Int. J. Document Anal. Recogn. (IJDAR) 2010 13 3 187-207

Digital Library

[9]

Donati L, Cesano S, and Prati A A complete hand-drawn sketch vectorization framework Multimed. Tools Appl. 2019 78 14 19083-19113

Digital Library

[10]

Ellis, K., Ritchie, D., Solar-Lezama, A., Tenenbaum, J.: Learning to infer graphics programs from hand-drawn images. In: Advances in Neural Information Processing Systems. pp. 6059–6068 (2018)

[11]

Favreau JD, Lafarge F, and Bousseau A Fidelity vs. simplicity: a global approach to line drawing vectorization ACM Trans. Graph. (TOG) 2016 35 4 120

Digital Library

[12]

Gao, J., Tang, C., Ganapathi-Subramanian, V., Huang, J., Su, H., Guibas, L.J.: Deepspline: Data-driven reconstruction of parametric curves and surfaces. arXiv preprint arXiv:1901.03781 (2019)

[13]

Guo Y, Zhang Z, Han C, Hu WB, Li C, and Wong TT Deep line drawing vectorization via line subdivision and topology reconstruction Comput. Graph. Forum 2019 38 81-90

[14]

Ha, D., Eck, D.: A neural representation of sketch drawings. arXiv preprint arXiv:1704.03477 (2018)

[15]

He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 770–778 (2016)

[16]

de las Heras L-P, Terrades OR, Robles S, and Sánchez G CVC-FP and SGT: a new database for structural floor plan analysis and its groundtruthing tool Int. J. Document Anal. Recogn (IJDAR) 2015 18 1 15-30

Digital Library

[17]

Hilaire X and Tombre K Robust and accurate vectorization of line drawings IEEE Trans. Pattern Anal. Mach. Intell. 2006 6 890-904

Digital Library

[18]

Kaiyrbekov, K., Sezgin, M.: Stroke-based sketched symbol reconstruction and segmentation. arXiv preprint arXiv:1901.03427 (2019)

[19]

Kansal R and Kumar S A vectorization framework for constant and linear gradient filled regions The Visual Comput. 2014 31 5 717-732

Digital Library

[20]

Kanungo T, Haralick RM, Baird HS, Stuezle W, and Madigan D A statistical, nonparametric methodology for document degradation model validation IEEE Trans. Pattern Anal. Mach. Intell. 2000 22 11 1209-1223

Digital Library

[21]

Kim, B., Wang, O., Öztireli, A.C., Gross, M.: Semantic segmentation for line drawing vectorization using neural networks. In: Computer Graphics Forum. vol. 37, pp. 329–338. Wiley Online Library (2018)

[22]

Koch, S., et al.: Abc: A big cad model dataset for geometric deep learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 9601–9611 (2019)

[23]

Li C, Liu X, and Wong TT Deep extraction of manga structural lines ACM Trans. Graph. (TOG) 2017 36 4 117

[24]

Liu, C., Wu, J., Kohli, P., Furukawa, Y.: Raster-to-vector: revisiting floorplan transformation. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2195–2203 (2017)

[25]

Liu, C., Schwing, A.G., Kundu, K., Urtasun, R., Fidler, S.: Rent3d: Floor-plan priors for monocular layout estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3413–3421 (2015)

[26]

Máttyus, G., Luo, W., Urtasun, R.: Deeproadmapper: Extracting road topology from aerial images. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 3438–3446 (2017)

[27]

Munusamy Kabilan, V., Morris, B., Nguyen, A.: Vectordefense: Vectorization as a defense to adversarial examples. arXiv preprint arXiv:1804.08529 (2018)

[28]

Najgebauer P and Scherer R Inertia-based fast vectorization of line drawings Comput. Graph. Forum 2019 38 203-213

[29]

Noris G, Hornung A, Sumner RW, Simmons M, and Gross M Topology-driven vectorization of clean line drawings ACM Trans. Graph. (TOG) 2013 32 1 4

Digital Library

[30]

Ronneberger O, Fischer P, and Brox T Navab N, Hornegger J, Wells WM, and Frangi AF U-Net: convolutional networks for biomedical image segmentation Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015 2015 Cham Springer 234-241

[31]

Rusiñol M, Borràs A, and Lladós J Relational indexing of vectorial primitives for symbol spotting in line-drawing images Pattern Recogn. Lett. 2010 31 3 188-201

Digital Library

[32]

Sasaki K, Iizuka S, SimoSerra E, and Ishikawa H Learning to restore deteriorated line drawing The Visual Comput. 2018 34 6–8 1077-1085

Digital Library

[33]

Selinger, P.: Potrace: a polygon-based tracing algorithm. Potrace. http://potrace.sourceforge.net/potrace.pdf (2003)

[34]

Sharma, D., Gupta, N., Chattopadhyay, C., Mehta, S.: Daniel: A deep architecture for automatic analysis and retrieval of building floor plans. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). vol. 1, pp. 420–425. IEEE (2017)

[35]

Simo-Serra E, Iizuka S, and Ishikawa H Mastering sketching: adversarial augmentation for structured prediction ACM Trans. Graph. (TOG) 2018 37 1 11

Digital Library

[36]

Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems. pp. 5998–6008 (2017)

[37]

Zhao, J., Feng, J., Zhou, B.: Image vectorization using blue-noise sampling. In: Imaging and Printing in a Web 2.0 World IV International Society for Optics and Photonics. vol. 8664, p. 86640H (2013)

[38]

Zheng, N., Jiang, Y., Huang, D.: Strokenet: Aneural painting environment. In: International Conference on Learning Representations (2018)

[39]

Zhou, T., et al.: Learning to doodle with stroke demonstrations and deep q-networks. In: BMVC. p. 13 (2018)

Cited By

Yan CLi YAneja DFisher MSimo-Serra EGingold Y(2024)Deep Sketch Vectorization via Implicit Surface ExtractionACM Transactions on Graphics10.1145/365819743:4(1-13)Online publication date: 19-Jul-2024
https://dl.acm.org/doi/10.1145/3658197
Zhou HZhang HWang B(2024)Segmentation-Guided Layer-Wise Image Vectorization with Gradient FillsComputer Vision – ECCV 202410.1007/978-3-031-72684-2_10(165-180)Online publication date: 29-Sep-2024
https://dl.acm.org/doi/10.1007/978-3-031-72684-2_10
Tiwari ABiswas SLladós J(2024)SketchGPT: Autoregressive Modeling for Sketch Generation and RecognitionDocument Analysis and Recognition - ICDAR 202410.1007/978-3-031-70549-6_25(421-438)Online publication date: 30-Aug-2024
https://dl.acm.org/doi/10.1007/978-3-031-70549-6_25
Show More Cited By

Recommendations

A circle-based vectorization algorithm for drawings with shadows
SBIM '13: Proceedings of the International Symposium on Sketch-Based Interfaces and Modeling

Vectorization algorithms described in the literature assume that the drawings being vectorized are either binary images or have a clear white background. Sketches of artistic objects however also contain shadows which help the artist to portray intent, ...
An approach to augmented reality technical drawings
SENSIG'09/VIS'09/MATERIALS'09: Proceedings of the 2nd WSEAS International Conference on Sensors, and Signals and Visualization, Imaging and Simulation and Materials Science

This paper presents a system based on Augmented Reality (AR) technologies that enables creation of a new class of technical drawings called Augmented Reality Technical Drawings (ARTD). With this system the users wearing a see-trough Head Mounted Display ...
Outer-loop vectorization: revisited for short SIMD architectures
PACT '08: Proceedings of the 17th international conference on Parallel architectures and compilation techniques

Vectorization has been an important method of using data-level parallelism to accelerate scientific workloads on vector machines such as Cray for the past three decades. In the last decade it has also proven useful for accelerating multi-media and ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings

Computer Vision – ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XIII

Aug 2020

839 pages

ISBN:978-3-030-58600-3

DOI:10.1007/978-3-030-58601-0

Editors:
Andrea Vedaldi
University of Oxford, Oxford, UK
,
Horst Bischof
Graz University of Technology, Graz, Austria
,
Thomas Brox
University of Freiburg, Freiburg im Breisgau, Germany
,
Jan-Michael Frahm
University of North Carolina at Chapel Hill, Chapel Hill, NC, USA

© Springer Nature Switzerland AG 2020.

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 23 August 2020

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

11
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 13 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Yan CLi YAneja DFisher MSimo-Serra EGingold Y(2024)Deep Sketch Vectorization via Implicit Surface ExtractionACM Transactions on Graphics10.1145/365819743:4(1-13)Online publication date: 19-Jul-2024
https://dl.acm.org/doi/10.1145/3658197
Zhou HZhang HWang B(2024)Segmentation-Guided Layer-Wise Image Vectorization with Gradient FillsComputer Vision – ECCV 202410.1007/978-3-031-72684-2_10(165-180)Online publication date: 29-Sep-2024
https://dl.acm.org/doi/10.1007/978-3-031-72684-2_10
Tiwari ABiswas SLladós J(2024)SketchGPT: Autoregressive Modeling for Sketch Generation and RecognitionDocument Analysis and Recognition - ICDAR 202410.1007/978-3-031-70549-6_25(421-438)Online publication date: 30-Aug-2024
https://dl.acm.org/doi/10.1007/978-3-031-70549-6_25
Kalleli STrigg SAlbouy SHusson MAubry M(2024)Historical Astronomical Diagrams Decomposition in Geometric PrimitivesDocument Analysis and Recognition - ICDAR 202410.1007/978-3-031-70543-4_7(108-125)Online publication date: 30-Aug-2024
https://dl.acm.org/doi/10.1007/978-3-031-70543-4_7
Myronova MNeveu WBessmeltsev M(2023)Differential Operators on Sketches via Alpha ContoursACM Transactions on Graphics10.1145/359242042:4(1-15)Online publication date: 26-Jul-2023
https://dl.acm.org/doi/10.1145/3592420
Liu CAoki TBessmeltsev MSheffer A(2023)StripMaker: Perception-driven Learned Vector Sketch ConsolidationACM Transactions on Graphics10.1145/359213042:4(1-15)Online publication date: 26-Jul-2023
https://dl.acm.org/doi/10.1145/3592130
Mohamed Moussa ELelore TMouchère H(2023)SET, SORT! A Novel Sub-stroke Level Transformers for Offline Handwriting to Online ConversionDocument Analysis and Recognition - ICDAR 202310.1007/978-3-031-41676-7_5(81-97)Online publication date: 21-Aug-2023
https://dl.acm.org/doi/10.1007/978-3-031-41676-7_5
Camba JCompany PNaya F(2022)Sketch-Based Modeling in Mechanical Engineering DesignComputer-Aided Design10.1016/j.cad.2022.103283150:COnline publication date: 1-Sep-2022
https://dl.acm.org/doi/10.1016/j.cad.2022.103283
Ganin YBartunov SLi YKeller ESaliceti SRanzato MBeygelzimer ADauphin YLiang PVaughan J(2021)Computer-aided design as languageProceedings of the 35th International Conference on Neural Information Processing Systems10.5555/3540261.3540711(5885-5897)Online publication date: 6-Dec-2021
https://dl.acm.org/doi/10.5555/3540261.3540711
Mohamed Moussa ELelore TMouchère H(2021)Applying End-to-End Trainable Approach on Stroke Extraction in Handwritten Math Expressions ImagesDocument Analysis and Recognition – ICDAR 202110.1007/978-3-030-86334-0_29(445-458)Online publication date: 5-Sep-2021
https://dl.acm.org/doi/10.1007/978-3-030-86334-0_29
Show More Cited By

View Options

View options

Figures

Tables

Media

View Table of Conten