Alert button
Picture for Maria Taktasheva

Maria Taktasheva

Alert button

Deep Vectorization of Technical Drawings

Mar 16, 2020
Vage Egiazarian, Oleg Voynov, Alexey Artemov, Denis Volkhonskiy, Aleksandr Safin, Maria Taktasheva, Denis Zorin, Evgeny Burnaev

Figure 1 for Deep Vectorization of Technical Drawings
Figure 2 for Deep Vectorization of Technical Drawings
Figure 3 for Deep Vectorization of Technical Drawings
Figure 4 for Deep Vectorization of Technical Drawings

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.

Viaarxiv icon

Learning to Approximate Directional Fields Defined over 2D Planes

Jul 01, 2019
Maria Taktasheva, Albert Matveev, Alexey Artemov, Evgeny Burnaev

Figure 1 for Learning to Approximate Directional Fields Defined over 2D Planes
Figure 2 for Learning to Approximate Directional Fields Defined over 2D Planes
Figure 3 for Learning to Approximate Directional Fields Defined over 2D Planes
Figure 4 for Learning to Approximate Directional Fields Defined over 2D Planes

Reconstruction of directional fields is a need in many geometry processing tasks, such as image tracing, extraction of 3D geometric features, and finding principal surface directions. A common approach to the construction of directional fields from data relies on complex optimization procedures, which are usually poorly formalizable, require a considerable computational effort, and do not transfer across applications. In this work, we propose a deep learning-based approach and study the expressive power and generalization ability.

* Proc. of AIST, 2019  
* 7 pages, 5 figures 
Viaarxiv icon