Oleh Rybkin

I am a Ph.D. student in the GRASP laboratory at the University of Pennsylvania, where I work on computer vision and deep learning with Kostas Daniilidis.

Previously, I received my bachelor's degree from Czech Technical University in Prague, where I was advised by Tomas Pajdla. I've spent two summers at INRIA and TiTech, with Josef Sivic and Akihiko Torii respectively.

Google Scholar  /  GitHub  /  Email  /  CV  /  LinkedIn

I am broadly interested in artificial intelligence, computer vision, and cognitive robotics. Recently, I've been working on machine understanding of motion and intuitive physics, with the ultimate goal of application to real-world robotic manipulation. During my bachelor's, I also worked on camera geometry for structure from motion.

Unsupervised Learning of Sensorimotor Affordances by Stochastic Future Prediction
Oleh Rybkin^*, Karl Pertsch^*, Andrew Jaegle, Kosta Derpanis, Kostas Daniilidis
project page / pdf coming soon / poster

The method learns possible actions that an environment admits from pure video data. This can be used e.g. to transplant a trajectory of actions from one video into another.

Hover the mouse here to see the video.

Predicting the Future with Transformational States
Andrew Jaegle, Oleh Rybkin, Kosta Derpanis, Kostas Daniilidis
ArXiv, 2018
project page / arXiv

The model predicts future video frames by learning to represent the present state of a system together with a high-level transformation that is used to produce its future state.

Hover the mouse here to see the video.

The reasonable ineffectiveness of pixel metrics for future prediction
2018

MSE loss and its variants are commonly used for training and evaluation of future prediction. But is this the right thing to do?

This guy has a cool website