Ing. Maroš Kollár

About

I am a PhD student at FIIT STU in Bratislava, under the supervision of Prof. Wanda Benešová. In research, I am interested in deep learning focused on generative models and computer vision. In my free time, I like to work on some Arduino projects and hang on the climbing wall (bouldering).

Research

Generative models, synthesis of textures, and medical images.

 

Examples of generated textures (results of my master thesis)

 

Publications

ORCID

  • Kollár, M.; Hudec, L. and Benesova, W. (2023). Multiclass Texture Synthesis Using Generative Adversarial Networks. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications – GRAPP, ISBN 978-989-758-634-7; ISSN 2184-4321, SciTePress, pages 87-97. DOI: 10.5220/0011657500003417 
    Abstract: Generative adversarial networks as a tool for generating content are currently one of the most popular
methods for content synthesis. Despite its popularity, multiple solutions suffer from the drawback of a shortage
of generality. It means that trained models can usually synthesize only one specific kind of output. The usual
synthesis approach for generating N different texture species requires training N models with changing training
data. However, few solutions explore the synthesis of multiple types of textures. In our work, we present an
alternative approach for multiclass texture synthesis. We focus on the synthesis of realistic natural non-stationary
textures. Our solution divides textures into classes based on the objects they represent and allows users to control
the class of synthesized textures and their appearance. Thanks to the controllable selections from latent space, we
also explore possibilities of creating transitions between classes of trained textures for potential better usage in
applications where texture synthesis is required.

Theses

  • Computer vision in medical applications
    Kollár, Maroš. Dissertation thesis: FIIT STU, ongoing
  • Multiclass texture synthesis using generative adversarial networks
    Kollár, Maroš. Diploma thesis. Bratislava: FIIT STU, 2022.
  • Personalized recommendation on the Web
    Kollár, Maroš. Bachelor thesis. Bratislava: FIIT STU, 2020.

Teaching

  • Digital Processing of Sound, Image, and Biosignals – Teaching Assistant
  • Neural Networks – Teaching Assistant