Radoslav Vargic
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Radoslav Vargic has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- A. Vrábel
Kedros a.s., Bratislava, Slovakia
1 shared publication - F. Husák
Kedros a.s., Bratislava, Slovakia
1 shared publication - Gregor Rozinaj
Faculty of Electrical Engineering and Information Technology, Slovak University of Technology in Bratislava, 84104 Bratislava, Slovakia
1 shared publication - Ivan Kotuliak
Faculty of Informatics and Information Technologies, Slovak University of Technology in Bratislava, Ilkovičova 2, 842 16 Bratislava, Slovakia
1 shared publication - Ivan Minárik
Faculty of Electrical Engineering and Information Technology, Slovak University of Technology in Bratislava, 84104 Bratislava, Slovakia
1 shared publication - Jarmila Pavlovicova
Faculty of Electrical Engineering and Information Technology, Slovak University of Technology in Bratislava, 841 04 Bratislava, Slovakia
1 shared publication
Latest Publications
- Open Access
- 8 April 2026
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 8 (4) , 94
Deep Learning-Driven Sparse Light Field Enhancement: A CNN-LSTM Framework for Novel View Synthesis and 3D Scene Reconstruction
Sparse light field imaging often limits the quality of 3D scene reconstruction due to insufficient viewpoint coverage, resulting in incomplete or inaccurate reconstructions. This work introduces a hybrid CNN–LSTM-based framework to address this issue by generating novel camera poses and the corresponding synthesized novel views, effectively densifying the light field representation. The CNN extracts spatial features from the sparse input views, while the LSTM predicts temporal and positional dependencies, enabling smooth interpolation of novel poses and views. The proposed method integrates these synthesized views with the original sparse dataset to produce a comprehensive set of images. Our approach was evaluated on several datasets, including challenging datasets. The inference capability of our method was tested extensively, and it showed good generalization across diverse datasets. The effectiveness of the framework was evaluated not only with local light field fusion (LLFF) but also with NeRF and 3D Gaussian Splatting, which are considered state-of-the-art reconstruction methods. Overall, the enriched dataset generated by our method led to consistent improvements in 3D reconstruction quality, including higher depth estimation accuracy, reduced artifacts, and enhanced structural consistency. Most importantly, LSTM-based approaches have so far attracted limited attention in the context of generating novel views. While LSTMs have been widely applied in sequential data domains such as natural language processing, their use for image generation conditioned on camera poses remains largely unexplored, which underscores the novelty and significance of the proposed work. This approach provides a scalable and generalizable solution to the sparsity problem in light fields, advancing the capabilities of computational imaging, photorealistic rendering, and immersive 3D scene reconstruction. The results firmly establish the proposed method as a robust and versatile tool for improving reconstruction quality in sparse-view settings.
- 8 April 2026
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 8 (4) , 94
Open AccessDeep Learning-Driven Sparse Light Field Enhancement: A CNN-LSTM Framework for Novel View Synthesis and 3D Scene Reconstruction
Sparse light field imaging often limits the quality of 3D scene reconstruction due to insufficient viewpoint coverage, resulting in incomplete or inaccurate reconstructions. This work introduces a hybrid CNN–LSTM-based framework to address this issue by generating novel camera poses and the corresponding synthesized novel views, effectively densifying the light field representation. The CNN extracts spatial features from the sparse input views, while the LSTM predicts temporal and positional dependencies, enabling smooth interpolation of novel poses and views. The proposed method integrates these synthesized views with the original sparse dataset to produce a comprehensive set of images. Our approach was evaluated on several datasets, including challenging datasets. The inference capability of our method was tested extensively, and it showed good generalization across diverse datasets. The effectiveness of the framework was evaluated not only with local light field fusion (LLFF) but also with NeRF and 3D Gaussian Splatting, which are considered state-of-the-art reconstruction methods. Overall, the enriched dataset generated by our method led to consistent improvements in 3D reconstruction quality, including higher depth estimation accuracy, reduced artifacts, and enhanced structural consistency. Most importantly, LSTM-based approaches have so far attracted limited attention in the context of generating novel views. While LSTMs have been widely applied in sequential data domains such as natural language processing, their use for image generation conditioned on camera poses remains largely unexplored, which underscores the novelty and significance of the proposed work. This approach provides a scalable and generalizable solution to the sparsity problem in light fields, advancing the capabilities of computational imaging, photorealistic rendering, and immersive 3D scene reconstruction. The results firmly establish the proposed method as a robust and versatile tool for improving reconstruction quality in sparse-view settings.
- Open Access
Structure and Base Analysis of Receptive Field Neural Networks in a Character Recognition Task
This paper explores extensions and restrictions of shallow convolutional neural networks with fixed kernels trained with a limited number of training samples. We extend the work recently done in research on Receptive Field Neural Networks (RFNN) and show their behaviour using different bases and step-by-step changes within the network architecture. To ensure the reproducibility of the results, we simplified the baseline RFNN architecture to a single-layer CNN network and introduced a deterministic methodology for RFNN training and evaluation. This methodology enabled us to evaluate the significance of changes using the (recently widely used in neural networks) Bayesian comparison. The results indicate that a change in the base may have less of an effect on the results than re-training using another seed. We show that the simplified network with tested bases has similar performance to the chosen baseline RFNN architecture. The data also show the positive impact of energy normalization of used filters, which improves the classification accuracy, even when using randomly initialized filters.
Open AccessStructure and Base Analysis of Receptive Field Neural Networks in a Character Recognition Task
This paper explores extensions and restrictions of shallow convolutional neural networks with fixed kernels trained with a limited number of training samples. We extend the work recently done in research on Receptive Field Neural Networks (RFNN) and show their behaviour using different bases and step-by-step changes within the network architecture. To ensure the reproducibility of the results, we simplified the baseline RFNN architecture to a single-layer CNN network and introduced a deterministic methodology for RFNN training and evaluation. This methodology enabled us to evaluate the significance of changes using the (recently widely used in neural networks) Bayesian comparison. The results indicate that a change in the base may have less of an effect on the results than re-training using another seed. We show that the simplified network with tested bases has similar performance to the chosen baseline RFNN architecture. The data also show the positive impact of energy normalization of used filters, which improves the classification accuracy, even when using randomly initialized filters.
- 1 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. CFP2255E-A, 1-4
An approach to EEG based BCI for motor imagery using time-frequency representation and CNN
In this contribution, we use electroencephalography for brain-computer interface and focus on two-class recognition of motor imagery data. We present a method with various modifications based on convolutional neural networks, we focus on time-frequency re8presentation of data. We use Short-Time Fourier Transform and Continuous Wavelet Transform. The method and its variation are tested on selected dataset and evaluated using cross-validation setup. The results show competitiveness of this method.
- 1 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. CFP2255E-A, 1-4
An approach to EEG based BCI for motor imagery using time-frequency representation and CNN
In this contribution, we use electroencephalography for brain-computer interface and focus on two-class recognition of motor imagery data. We present a method with various modifications based on convolutional neural networks, we focus on time-frequency re8presentation of data. We use Short-Time Fourier Transform and Continuous Wavelet Transform. The method and its variation are tested on selected dataset and evaluated using cross-validation setup. The results show competitiveness of this method.
- 2 March 2022
- Published by Springer Nature
- p. 185-197
An Approach for BCI Using Motor Imagery Based on Wavelet Transform and Convolutional Neural Network
- 2 March 2022
- Published by Springer Nature
- p. 185-197
An Approach for BCI Using Motor Imagery Based on Wavelet Transform and Convolutional Neural Network
- 14 February 2018
- Published by Springer Nature
- p. 421-430
Advanced Interactive Multimedia Delivery in 5G Networks
- 14 February 2018
- Published by Springer Nature
- p. 421-430
Advanced Interactive Multimedia Delivery in 5G Networks
- 18 October 2011
- Published by Springer Nature in Telecommunication Systems
- Vol. 52 (3) , 1705-1711
Provisioning of VoIP services for mobile subscribers using WiFi access network
- 18 October 2011
- Published by Springer Nature in Telecommunication Systems
- Vol. 52 (3) , 1705-1711
Provisioning of VoIP services for mobile subscribers using WiFi access network