16 citations · 20 across the 4 of their papers we have counts for
4 papers
DeepLandscape: Adversarial Modeling of Landscape Video
Elizaveta Logacheva, Roman Suvorov, Oleg Khomenko +2
We build a new model of landscape videos that can be trained on a mixture of static landscape images as well as landscape animations. Our architecture extends StyleGAN model by aug…
Learning State Representations in Complex Systems with Multimodal Data
Pavel Solovev, Vladimir Aliev, Pavel Ostyakov +7
Representation learning becomes especially important for complex systems with multimodal data sources such as cameras or sensors. Recent advances in reinforcement learning and opti…
SEIGAN: Towards Compositional Image Generation by Simultaneously Learning to Segment, Enhance, and Inpaint
Pavel Ostyakov, Roman Suvorov, Elizaveta Logacheva +2
We present a novel approach to image manipulation and understanding by simultaneously learning to segment object masks, paste objects to another background image, and remove them f…
Label Denoising with Large Ensembles of Heterogeneous Neural Networks
Pavel Ostyakov, Elizaveta Logacheva, Roman Suvorov +4
Despite recent advances in computer vision based on various convolutional architectures, video understanding remains an important challenge. In this work, we present and discuss a…