Valeria Efimova
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Valeria Efimova has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Andrey Filchenkov
ITMO University
4 shared publications - Viacheslav Shalamov
ITMO University Saint-Petersburg Russia
4 shared publications - Andrey Filchenkov
GO AI LAB, St Petersburg, Russia
3 shared publications - Ivan Jarsky
ITMO University, Saint-Petersburg, Russia
3 shared publications - Anatoly Shalyto
ITMO University
2 shared publications - Ivan Jarsky
ITMO University, St Petersburg, Russia
2 shared publications
Latest Publications
- 21 April 2026
- Published by Elsevier in Optics and Lasers in Engineering
- Vol. 203
Cal-Sal ordering of Hadamard patterns for efficient single-pixel object tracking
- 21 April 2026
- Published by Elsevier in Optics and Lasers in Engineering
- Vol. 203
Cal-Sal ordering of Hadamard patterns for efficient single-pixel object tracking
- Open Access
Text-to-Vector Conversion for Residential Plan Design
Computer graphics, comprising both raster and vector components, is a fundamental part of modern science, industry, and digital communication. While raster graphics offer ease of use, its pixel-based structure limits scalability. Vector graphics, defined by mathematical primitives, provides scalability without quality loss, however, it is more complex to produce. For design and architecture, the versatility of vector graphics is paramount, despite its computational demands. This paper introduces a novel method for generating vector residential plans from textual descriptions. Our approach surpasses existing solutions by approximately 5% in CLIPScore-based visual quality, benefiting from its inherent handling of right angles and flexible settings. Additionally, we present a new algorithm for vectorizing raster plans into structured vector images. Such images have a better CLIPscore compared to others by about 4%.
Open AccessText-to-Vector Conversion for Residential Plan Design
Computer graphics, comprising both raster and vector components, is a fundamental part of modern science, industry, and digital communication. While raster graphics offer ease of use, its pixel-based structure limits scalability. Vector graphics, defined by mathematical primitives, provides scalability without quality loss, however, it is more complex to produce. For design and architecture, the versatility of vector graphics is paramount, despite its computational demands. This paper introduces a novel method for generating vector residential plans from textual descriptions. Our approach surpasses existing solutions by approximately 5% in CLIPScore-based visual quality, benefiting from its inherent handling of right angles and flexible settings. Additionally, we present a new algorithm for vectorizing raster plans into structured vector images. Such images have a better CLIPscore compared to others by about 4%.
- 10 February 2026
- Published by Springer Nature
- p. 356-372
Advancements in Vector Graphics Generation for Music Cover Art
- 10 February 2026
- Published by Springer Nature
- p. 356-372
Advancements in Vector Graphics Generation for Music Cover Art
- 13 October 2025
- Published by Springer Nature
- p. 322-332
Language-Specific Adaptation Strategies for Speaker Recognition Using MobileNet
- 13 October 2025
- Published by Springer Nature
- p. 322-332
Language-Specific Adaptation Strategies for Speaker Recognition Using MobileNet
- Open Access
- 1 December 2024
- Published by ITMO University in Scientific and Technical Journal of Information Technologies, Mechanics and Optics
- Vol. 24 (6) , 972
Surface defect detection with limited data based on SSD detector and Siamese networks
This study presents an algorithm for the problem of detecting defects on hard surfaces when trained with zero or a small number of examples, addressing the challenge of limited data availability. The existing defect detection methodology using machine vision is enhanced. A hybrid approach is proposed, combining the strengths of the SSD detector and Siamese Neural Networks (SNN). The SSD detector extracts feature vector representations from images, while the SNNs are used to construct the feature space. The new approach demonstrates high accuracy in detecting both known and previously unseen defects in the training dataset. Based on testing across seven different datasets, the model showed good performance in scenarios with a limited number of training examples. A comparative analysis with existing models highlights the high performance of the proposed approach and its potential as an innovative and effective solution for the universal detection of defects on hard surfaces.
- 1 December 2024
- Published by ITMO University in Scientific and Technical Journal of Information Technologies, Mechanics and Optics
- Vol. 24 (6) , 972
Open AccessSurface defect detection with limited data based on SSD detector and Siamese networks
This study presents an algorithm for the problem of detecting defects on hard surfaces when trained with zero or a small number of examples, addressing the challenge of limited data availability. The existing defect detection methodology using machine vision is enhanced. A hybrid approach is proposed, combining the strengths of the SSD detector and Siamese Neural Networks (SNN). The SSD detector extracts feature vector representations from images, while the SNNs are used to construct the feature space. The new approach demonstrates high accuracy in detecting both known and previously unseen defects in the training dataset. Based on testing across seven different datasets, the model showed good performance in scenarios with a limited number of training examples. A comparative analysis with existing models highlights the high performance of the proposed approach and its potential as an innovative and effective solution for the universal detection of defects on hard surfaces.
- 1 October 2024
- Published by Springer Nature in Journal of Mathematical Sciences
- Vol. 285 (2) , 169-179
Vector Graphics Generation with LLMs: Approaches and Models
- 1 October 2024
- Published by Springer Nature in Journal of Mathematical Sciences
- Vol. 285 (2) , 169-179
Vector Graphics Generation with LLMs: Approaches and Models
- 1 October 2024
- Published by Springer Nature in Journal of Mathematical Sciences
- Vol. 285 (2) , 155-168
Image Vectorization: a Review
- 1 October 2024
- Published by Springer Nature in Journal of Mathematical Sciences
- Vol. 285 (2) , 155-168
Image Vectorization: a Review
- Open Access
- 14 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2083-2086
Evolutionary image vectorization with variable curve number
Vector and raster graphics are the two main types of 2D graphics. Raster graphics operate images consisting of pixels (dots); vector images are created using mathematical objects such as lines, curves, and shapes. The main advantage of vector graphics is that it can be scaled without loss of quality, which is useful for advertising, design, frontend development, and other fields of application. At the moment, the issue of vectorization (conversion from raster to vector graphics) has not been fully resolved. Existing approaches are not able to work with a color gradient and they have other disadvantages, such as artifacts, inaccurate result correspondence to the original raster image, and extremely long processing time. To solve these problems, we propose an evolutionary algorithm for image vectorization. The main idea of our approach is to iteratively improve vector images using mutations and crossovers. The algorithm itself does not require any parameters, such as curve number, other than the original image, which makes it universal. The results of comparison with existing solutions show that our algorithm qualitatively and quickly vectorizes images, outperforms others in terms of pixel-by-pixel MSE by 15% and does not generate unnecessary shapes in the resulting vector image.
- 14 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2083-2086
Open AccessEvolutionary image vectorization with variable curve number
Vector and raster graphics are the two main types of 2D graphics. Raster graphics operate images consisting of pixels (dots); vector images are created using mathematical objects such as lines, curves, and shapes. The main advantage of vector graphics is that it can be scaled without loss of quality, which is useful for advertising, design, frontend development, and other fields of application. At the moment, the issue of vectorization (conversion from raster to vector graphics) has not been fully resolved. Existing approaches are not able to work with a color gradient and they have other disadvantages, such as artifacts, inaccurate result correspondence to the original raster image, and extremely long processing time. To solve these problems, we propose an evolutionary algorithm for image vectorization. The main idea of our approach is to iteratively improve vector images using mutations and crossovers. The algorithm itself does not require any parameters, such as curve number, other than the original image, which makes it universal. The results of comparison with existing solutions show that our algorithm qualitatively and quickly vectorizes images, outperforms others in terms of pixel-by-pixel MSE by 15% and does not generate unnecessary shapes in the resulting vector image.
- Open Access
Image Vectorization: a Review
Nowadays, there are many diffusion and autoregressive models that show impressive results for generating images from text and other input domains. However, these methods are not intended for ultra-high-resolution image synthesis. Vector graphics are devoid of this disadvantage, so the generation of images in this format looks very promising. Instead of generating vector images directly, you can first synthesize a raster image and then apply vectorization. Vectorization is the process of converting a raster image into a similar vector image using primitive shapes. Besides being similar, generated vector image is also required to contain the minimum number of shapes for rendering. In this paper, we focus specifically on machine learning-compatible vectorization methods. We are considering Mang2Vec, Deep Vectorization of Technical Drawings, DiffVG, and LIVE models. We also provide a brief overview of existing online methods. We also recall other algorithmic methods, Im2Vec and ClipGEN models, but they do not participate in the comparison, since there is no open implementation of these methods or their official implementations do not work correctly. Our research shows that despite the ability to directly specify the number and type of shapes, existing machine learning methods work for a very long time and do not accurately recreate the original image. We believe that there is no fast universal automatic approach and human control is required for every method.
Open AccessImage Vectorization: a Review
Nowadays, there are many diffusion and autoregressive models that show impressive results for generating images from text and other input domains. However, these methods are not intended for ultra-high-resolution image synthesis. Vector graphics are devoid of this disadvantage, so the generation of images in this format looks very promising. Instead of generating vector images directly, you can first synthesize a raster image and then apply vectorization. Vectorization is the process of converting a raster image into a similar vector image using primitive shapes. Besides being similar, generated vector image is also required to contain the minimum number of shapes for rendering. In this paper, we focus specifically on machine learning-compatible vectorization methods. We are considering Mang2Vec, Deep Vectorization of Technical Drawings, DiffVG, and LIVE models. We also provide a brief overview of existing online methods. We also recall other algorithmic methods, Im2Vec and ClipGEN models, but they do not participate in the comparison, since there is no open implementation of these methods or their official implementations do not work correctly. Our research shows that despite the ability to directly specify the number and type of shapes, existing machine learning methods work for a very long time and do not accurately recreate the original image. We believe that there is no fast universal automatic approach and human control is required for every method.
- Open Access
Neural Style Transfer for Vector Graphics
Neural style transfer draws researchers' attention, but the interest focuses on bitmap images. Various models have been developed for bitmap image generation both online and offline with arbitrary and pre-trained styles. However, the style transfer between vector images has not almost been considered. Our research shows that applying standard content and style losses insignificantly changes the vector image drawing style because the structure of vector primitives differs a lot from pixels. To handle this problem, we introduce new loss functions. We also develop a new method based on differentiable rasterization that uses these loss functions and can change the color and shape parameters of the content image corresponding to the drawing of the style image. Qualitative experiments demonstrate the effectiveness of the proposed VectorNST method compared with the state-of-the-art neural style transfer approaches for bitmap images and the only existing approach for stylizing vector images, DiffVG. Although the proposed model does not achieve the quality and smoothness of style transfer between bitmap images, we consider our work an important early step in this area. VectorNST code and demo service are available at https://github.com/IzhanVarsky/VectorNST.
Open AccessNeural Style Transfer for Vector Graphics
Neural style transfer draws researchers' attention, but the interest focuses on bitmap images. Various models have been developed for bitmap image generation both online and offline with arbitrary and pre-trained styles. However, the style transfer between vector images has not almost been considered. Our research shows that applying standard content and style losses insignificantly changes the vector image drawing style because the structure of vector primitives differs a lot from pixels. To handle this problem, we introduce new loss functions. We also develop a new method based on differentiable rasterization that uses these loss functions and can change the color and shape parameters of the content image corresponding to the drawing of the style image. Qualitative experiments demonstrate the effectiveness of the proposed VectorNST method compared with the state-of-the-art neural style transfer approaches for bitmap images and the only existing approach for stylizing vector images, DiffVG. Although the proposed model does not achieve the quality and smoothness of style transfer between bitmap images, we consider our work an important early step in this area. VectorNST code and demo service are available at https://github.com/IzhanVarsky/VectorNST.