The Machine Learning Lab (MLLab) was founded in 2018. It is a part of the Faculty of Applied Sciences, Ukrainian Catholic University in Lviv. Our research has several branches of focus and we are constantly expanding and looking for new challenges. Сurrently, we are working on: machine learning and deep learning algorithms applied to the supervised and weakly-supervised visual recognition problems; robust single view geometry estimation; reinforcement learning for optimization and control problems. Our research center has well-established connections with industry and academia.
FEAR: Fast, Efficient, Accurate and Robust Visual Tracker
ARXIV: https://arxiv.org/abs/2112.07957
Автори: Vasyl Borsuk, Roman Vei, Orest Kupyn, Tetiana Martyniuk, Igor Krashenyi, Jiři Matas
Конференція/Журнал: European Conference on Computer Vision
Is Mapping Necessary for Realistic PointGoal Navigation?
ARXIV: https://arxiv.org/abs/2206.00997
Вебсайт: https://rpartsey.github.io/pointgoalnav/
Автори: Ruslan Partsey, Erik Wijmans, Naoki Yokoyama, Oles Dobosevych, Dhruv Batra, Oleksandr Maksymets
Конференція/Журнал: IEEE/CVF Conference on Computer Vision and Pattern Recognition
DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image
ARXIV: https://arxiv.org/abs/2204.03688
Вебсайт: https://www.pinatafarm.com/research/dad-3dheads
Автори: Tetiana Martyniuk, Orest Kupyn, Yana Kurlyak, Igor Krashenyi, Jiři Matas, Viktoriia Sharmanska
Конференція/Журнал: IEEE/CVF Conference on Computer Vision and Pattern Recognition
OpenGlue: Open Source Graph Neural Net Based Pipeline for Image Matching
ARXIV: https://arxiv.org/pdf/2204.08870.pdf
Автори: Ostap Viniavskyi, Mariia Dobko, Oles Dobosevych
Minimal Solvers for Single-View Lens-Distorted Camera Auto-Calibration
ARXIV: https://arxiv.org/abs/2011.08988
Автори: Yaroslava Lochman, Oles Dobosevych, Rostyslav Hryniv, James Pritts
Конференція/Журнал: IEEE/CVF Winter Conference on Applications of Computer Vision
Weakly-supervised segmentation for disease localization in chest x-ray images
ARXIV: https://arxiv.org/abs/2007.00748
Автори: Ostap Viniavskyi, Mariia Dobko, Oles Dobosevych
Конференція/Журнал: International Conference on Artificial Intelligence in Medicine
ActGAN: Flexible and Efficient One-shot Face Reenactment
ARXIV: https://arxiv.org/pdf/2003.13840
Автори: Ivan Kosarevych, Marian Petruk, Markian Kostiv, Orest Kupyn, Mykola Maksymenko, Volodymyr Budzan
Конференція/Журнал: 8th International Workshop on Biometrics and Forensics
DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
ARXIV: https://arxiv.org/abs/1908.03826
Автори: Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang
Конференція/Журнал: IEEE/CVF International Conference on Computer Vision
Deblurgan: Blind motion deblurring using conditional adversarial networks
ARXIV: https://arxiv.org/abs/1711.07064
Автори: Orest Kupyn, Volodymyr Budzan, Mykola Mykhailych, Dmytro Mishkin, Jiří Matas
Конференція/Журнал: IEEE/CVF Conference on Computer Vision and Pattern Recognition
