Tomas Kerepecky

PhD student, Institute of Information Theory and Automation, Czech Academy of Sciences

Hello! I am currently PhD student on Image processing at the Institute of Information Theory and Automation cooperating institute of Czech Technical University, Prague. Furthermore, I am working toward an M.A. degree in Practical theology - Leadership concentration at TCM International Institute, Austria. In 2022, I received Fulbright-Masaryk award and did research at Washington University in St. Louis, US. I received the M.Sc. degree in Computational physics from the Faculty of Nuclear Sciences and Physical Engineering, Czech Technical University, in 2017.

I am School council member and visiting teacher at New Hope Mission School, Bihar, India. Since 2015 I hold the position of executive director of non-profit Christian organization focused on experiential education.

Education.

  • 2019-now

    Department of Mathematics, Czech Technical University in Prague, Czechia

    PhD student in Mathematical Engineering. Focusing on Image processing.

  • 2018-now

    TCM International Institute, Vienna, Austria.

    MA student in Practical Theology concentrated on Leadership studies.

  • 2015-2019

    Department of Physical Electronics, Czech Technical University in Prague, Czechia

    M.Sc. degree in Computational physics. Master thesis: Inverse Compton scattering by laser-accelerated electrons.

    PhD student in Computational physics till 2019.

Research interests.

Image restoration

Imaging plays a key role in many diverse areas. Due to imperfections of measuring devices, captured images suffer from image degradation. Image restoration methods try to improve their quality.

Imaging plays a key role in many diverse areas, such as astronomy, remote sensing, microscopy or tomography, just to name few. Due to imperfections of measuring devices (optical degradations, limited size of sensors, camera shake) and instability of observed scene (object motion, air turbulence), captured images are blurred, noisy and of insufficient spatial or temporal resolution. Image restoration methods try to improve their quality. For principle reasons, these methods need to know the type of degradation process and make less or more restrictive assumptions about the scene or the image we want to get. Intuitively, the more restrictions we are able to prescribe the better results we can achieve. Very general ones are for example simple smoothing constraints assuming that the image contains large homogenous areas. More restrictive are those allowing only a certain type of blurring (out-of-focus or motion blur in a certain direction) or for example the assumption that the whole scene is planar. Another possibility which makes the problem easier is to consider more than one image of the same scene (multiframe imaging). In this case, we need much less additional knowledge about the scene or degradation process.

See more:

Restoration of degraded images

Video processing

The main application of digital video processing is to provide high-quality visible-light videos for human consumption. It encompasses many approaches that derive from the essential principles of digital image processing.

The main application of digital video processing is to provide high-quality visible-light videos for human consumption. Digital video processing encompasses many approaches that derive from the essential principles of digital image processing (Alan C. Bovik).

I am currently focusing on object (face) detection, face recognition, object tracking and scene boundary detections. In foreseeable future I would like to do my research in temporal super-resolution.

Machine learning

Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed.

Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. Machine learning focuses on the development of computer programs that can access data and use it learn for themselves. The process of learning begins with observations or data, such as examples, direct experience, or instruction, in order to look for patterns in data and make better decisions in the future based on the examples that we provide. The primary aim is to allow the computers learn automatically without human intervention or assistance and adjust actions accordingly.

See more:

What is machine learning?

Servant leadership

Servant leadership is the book as well as the new idea which was presented by Robert Greenleaf in 1970. He says that “the great leader is seen as a servant first, and that simple fact is the key to his greatness.”

Servant leadership is the book as well as the new idea which was presented by Robert Greenleaf in 1970. He says that “the great leader is seen as a servant first, and that simple fact is the key to his greatness.” “Being servant means that one is dedicated to the growth of others and is committed to building values-driven relationships.” In the similar vein, James C. Hunter, in his book The Servant, defines leadership as “The skill of influencing people to work enthusiastically toward goals identified as being for the common good. “ John Milton then summarizes this concept by asking the question: “Is not every servant a leader because of influence by example?” Although R. Greenleaf first coined the phrase servant leadership, the idea comes originally from the Bible. In the New Testament Jesus says: “You know that the rulers of the Gentiles lord it over them, and their high officials exercise authority over them. Not so with you. Instead, whoever wants to become great among you must be your servant, and whoever wants to be first must be your slave - just as the Son of Man did not come to be served, but to serve, and to give his life as a ransom for many” (Matthew 20:25-28 NIV).

I study servant leadership theoretically and also practically:

TCM International Institute Non-profit Atleti v Akci, z.s.

I am really interested in image processing, leadership research and learning through experience and reflection.

Experiential education

Challenge and experience followed by reflection leading to learning and growth.

What is experiential education?

Challenge and experience followed by reflection leading to learning and growth.

Experiential education is a teaching philosophy that informs many methodologies in which educators purposefully engage with learners in direct experience and focused reflection in order to increase knowledge, develop skills, clarify values, and develop people's capacity to contribute to their communities.

See more on:

Association of Experiential Education Czech Experiential Learning Centre

I am the leader of Czech non-profit experiential education organization:

Atleti v Akci, z.s.

Publications.

Dual-Cycle: Self-Supervised Dual-View Fluorescence Microscopy Image Reconstruction using CycleGAN

Preprint

Three-dimensional fluorescence microscopy often suffers from anisotropy, where the resolution along the axial direction is lower than that within the lateral imaging plane. We address this issue by presenting Dual-Cycle, a new framework for joint deconvolution and fusion of dual-view fluorescence images. Inspired by the recent Neuroclear method, Dual-Cycle is designed as a cycle-consistent generative network trained in a self-supervised fashion by combining a dual-view generator and prior-guided degradation model. We validate Dual-Cycle on both synthetic and real data showing its state-of-the-art performance without any external training data.

Read the article

D3Net: Joint Demosaicking, Deblurring and Deringing

Accepted to 25th International Conference on Pattern Recognition (ICPR2020)

Images acquired with standard digital cameras have Bayer patterns and suffer from lens blur. A demosaicking step is implemented in every digital camera, yet blur often remains unattended due to computational cost and instability of deblurring algorithms. Linear methods, which are computationally less demanding, produce ringing artifacts in deblurred images. Complex non-linear deblurring methods avoid artifacts, however their complexity imply offline application after camera demosaicking, which leads to sub-optimal performance. In this work, we propose a joint demosaicking deblurring and deringing network with a light-weight architecture inspired by the alternating direction method of multipliers. The proposed network has a transparent and clear interpretation compared to other black-box data driven approaches. We experimentally validate its superiority over state-of-the-art demosaicking methods with offline deblurring.

Read the article

Iterative Wiener Filtering for Deconvolution with Ringing Artifact Suppression

2019 27th European Signal Processing Conference (EUSIPCO)

Sensor and lens blur degrade images acquired by digital cameras. Simple and fast removal of blur using linear filtering, such as Wiener filter, produces results that are not acceptable in most of the cases due to ringing artifacts close to image borders and around edges in the image. More elaborate deconvolution methods with non-smooth regularization, such as total variation, provide superior performance with less artifacts, however at a price of increased computational cost. We consider the alternating directions method of multipliers, which is a popular choice to solve such non-smooth convex problems, and show that individual steps of the method can be decomposed to simple filtering and element-wise operations. Filtering is performed with two sets of filters, called restoration and update filters, which are learned for the given type of blur and noise level with two different learning methods. The proposed deconvolution algorithm is implemented in the spatial domain and can be easily extended to include other restoration tasks such as demosaicing and super-resolution. Experiments demonstrate performance of the algorithm with respect to the size of learned filters, number of iterations, noise level and type of blur.

Read the article

Inverse Compton scattering by laser-accelerated electrons

Czech Technical University in Prague. Computing and Information Centre, 2017

This thesis deals with the study of X- and -radiation during the interaction of relativistic electrons with the intense electromagnetic field. This mechanism is called inverse Compton scattering. For the purpose of examining the properties of radiation from inverse Compton scattering, a new COCO code has been implemented. Radiation spectrum is computed through the use of fast Fourier transform of the radiation field of electrons.

Read the thesis

Teaching.

Contact.

kerepecky@utia.cas.cz skype: live:kerepecky_1 +420 266 052 864
  • Filip Sroubek's Lab,
  • Department of Image Processing,
  • Institute of Information Theory and Automation,
  • Czech Academy of Sciences.