Vladimir Yugay

I am a PhD candidate in Computer Vision Group at the University of Amsterdam under the supervision of Martin R. Oswald. My research interests lie in 3D computer vision, particularly 3D scene representation and SLAM. Before, I earned my master’s degree in data engineering and analytics from Technical University of Munich during which I was part of the research group from Laura Leal-Taixé. There, I was working on multiple object tracking in 3D.

During my master studies I also worked on 3D human body modelling as part of Kaia Health. There we achieved great results in helping people with chronic backpain by means of AI and computer vision.

Generally, I'm interested in 3D reconstruction of changing, dynamic environments. Currently, I am focused on making neural SLAM more efficient and working in the wild.

Publications

FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training
NeurIPS 2024

Ruihong Yin, Vladimir Yugay, Yue Li, Sezer Karaoglu, Theo Gevers
[arXiv]
Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting
Vladimir Yugay, Yue Li, Theo Gevers, Martin R. Oswald
[Project Page] [arXiv] [Code]
Loopy-SLAM: Dense Neural SLAM with Loop Closures
CVPR 2024

Lorenzo Iso, Erik Sandström, Vladimir Yugay, Luc Van Gool, Martin R. Oswald
[Project Page] [arXiv] [Code]
Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?
NeurIPS 2022

Patrick Dendorfer, Vladimir Yugay, Aljosa Osep, Laura Leal-Taixé
[Paper] [arXiv] [Code]