Enabling Visual Composition and Animation in Unsupervised Video Generation
A model to compose and animate scenes from sparse sets of visual features.
I am a Ph.D. student in the Computer Vision Group at the University of Bern, supervised by Prof. Dr. Paolo Favaro. I received my Specialist degree in Fundamental Mathematics and Mechanics at the Lomonosov Moscow State University in 2020. I also graduated from the Yandex School of Data Analysis in 2018. My topics of interest include Machine Learning, Computer Vision, Deep Learning and Generative Modeling.
A model to compose and animate scenes from sparse sets of visual features.
A model to animate single frames with sparse motion control.
Single image to novel view synthesis without any supervision.
Conditioning only on a few randomly chosen past frames at each denoising step of flow matching results into a more efficient training procedure.
A model to discover agents' action spaces from a dataset of videos in an unsupervised way. The action spaces are decomposed into global (2D shifts) and local (discrete) actions.
A neural network optimization algorithm based on Kalman filtering.