My name is Michal Neoral and I am a researcher at the Center for Machine Perception (CMP), Czech Technical University in Prague, in the Visual Recognition Group (VRG) at the Faculty of Electrical Engineering. I completed my Ph.D. in 2025 under the supervision of prof. Jiří Matas and Dr. Jan Šochman. My dissertation, Dense Motion Estimation in a Monocular Video, covers dense pixel-level tracking in video, with emphasis on optical flow estimation, occlusion handling, and motion segmentation. My broader research interests lie in long-term correspondence estimation, where I aim to develop robust methods that maintain temporal consistency across extended video sequences. More recently I have been working on detection, classification and fine-grained recognition for fast processing of large-scale data, in the AISee, Median, CEDMO, FunDive and Local CLS projects. During my Ph.D. I had the opportunity to collaborate with Toyota Motor Europe, and I would like to sincerely thank them for their generous support throughout my doctoral studies.

Updates

Education

All three degrees are from the Faculty of Electrical Engineering, Czech Technical University in Prague. Theses and supervisors are listed on the about page.

• Ph.D., Informatics / Artificial Intelligence and Biocybernetics, 2018 -- 2025
• Ing. (MSc equivalent), Open Informatics, specialization Computer Vision and Image Processing, 2014 -- 2017
• Bc. (BSc equivalent), Cybernetics and Robotics, specialization Robotics, 2011 -- 2014