Publications

Main Publications

• Multi-Flow Tracker with Independent Matching Quality Estimation
  Jonáš Šerých, Michal Neoral, and Jiří Matas
  Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, February 2025, Tuscon, Arizona USA.
  
  pdf
  arXiv
  supplementary
  code
  project page


• MFT: Long-term Tracking of Every Pixel
  Michal Neoral, Jonáš Šerých, and Jiří Matas
  Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 6837–6847, January 2024, Waikoloa, Hawaii USA.
  
  pdf
  arXiv
  supplementary
  code
  project page


• Monocular Arbitrary Moving Object Discovery and Segmentation
  Michal Neoral, Jan Šochman, and Jiří Matas
  In The 32nd British Machine Vision Conference, November 2021, Online.
  
  pdf
  code


• Continual Occlusion and Optical Flow Estimation
  Michal Neoral, Jan Šochman, and Jiří Matas
  Computer Vision – ACCV 2018. Ed. by C.V. Jawahar et al. Cham: Springer International Publishing, 2019, pp. 159–174. ISBN: 978-3-030-20870-7.
  
  pdf
  arXiv


• Object Scene Flow with Temporal Consistency
  Michal Neoral, and Jan Šochman
  In 22nd Computer Vision Winter Workshop (CVWW) Pattern Recognition and Image Processing Group; TU Wien \& PRIP Club; Vienna; Austria, February 2017, ISBN: 978-3-200-04969-7.
  
  pdf

Other Publications

• Point Tracking in Surgery–The 2024 Surgical Tattoos in Infrared (STIR) Challenge
  Adam Schmidt, Mert Asim Karaoglu, Soham Sinha, Mingang Jang, Ho-Gun Ha, Kyungmin Jung, Kyeongmo Gu, Ihsan Ullah, Hyunki Lee, Jonáš Šerých, Michal Neoral, Jiří Matas, Rulin Zhou, Wenlong He, An Wang, Hongliang Ren, Bruno Silva, Sandro Queiros, Estevao Lima, Joao L. Vilac, Shunsuke Kikuchi, Atsushi Kouno, Hiroki Matsuzaki, Tongtong Li, Yulu Chen, Ling Li, Xiang Ma, Xiaojian Li, Mona Sheikh Zeinoddin, Xu Wang, Zafer Tandogdu, Greg Shaw, Evangelos Mazomenos, Danail Stoyanov, Yuxin Chen, Zijian Wu, Alexander Ladikos, Simon DiMaio, Septimiu E. Salcudean, and Omid Mohareri
  
  pdf
  arXiv
  project page

Theses

• Dense Motion Estimation in a Monocular Video
  Michal Neoral, supervisor: prof. Ing. Jiří Matas, Ph.D., co-supervisor: Mgr. Jan Šochman, Ph.D.
  2025 Dissertation, in review process


• Object Scene Flow in Video Sequences
  Michal Neoral, supervisor: Mgr. Jan Šochman, Ph.D.
  2017 Master Thesis, awarded with the Dean's Prize for outstanding master thesis.


• Extraction of Features from Moving Garment
  Michal Neoral, supervisor: Ing. Pavel Krsek, Ph.D.
  2014 Bachelor Thesis.

Patents and Patent Applications

• MONOCULAR-VISION-BASED DETECTION OF MOVING OBJECTS
  Nikolay Chumerin, Michal Neoral, Jan Šochman, and Jiří Matas (2023).
  EP Patent EP4174770B1, filed Oct 28, 2021, and issued Nov 29, 2023. Granted Patent


• A METHOD AND SYSTEM FOR TRACKING A PIXEL IN A VIDEO
  Nikolay Chumerin, Jonáš Šerých, Michal Neoral, and Jiří Matas. (2024).
  EP Patent EP4465239A1, filed May 16, 2023, and issued Nov 20, 2024. Patent Application


• MONOCULAR-VISION-BASED DETECTION OF MOVING OBJECTS
  Nikolay Chumerin, Michal Neoral, Jan Šochman, and Jiří Matas. (2023).
  EP Patent EP4174770A1, filed Oct 28, 2021, and issued May 03, 2023. Patent Application


• METHODS FOR OPTICAL FLOW ESTIMATION
  Jan Šochman, Nikolay Chumerin, Jiří Matas, and Michal Neoral. (2020).
  WO Patent WO2020088766A1, filed Oct 31, 2018, and issued May 07, 2020. Patent Application